An intelligent recommendation method and system for corrugated carton packaging production process

Abstract

The present invention discloses an intelligent recommendation method and system for a corrugated paperboard packaging production process, including obtaining order feature data of target customers and inputting them into a multi-objective optimization model to obtain an initial recommendation plan, evaluating the first matching degree between the order and the customer demand progress, adjusting the order priority if the requirements are not met, and otherwise evaluating the second matching degree between the raw material supply and the customer demand, matching the associated production process for the initial recommendation plan when the conditions are not met, and generating a target recommendation plan; executing and configuring the initial parameters of the production process according to the target recommendation plan, obtaining the actual operating parameters of the production line in real time and drawing a change curve, predicting the production operation status and determining the parameter compensation factor, and updating the initial parameters of the production process. The present invention adjusts the initial recommendation plan according to the matching degree of the production process progress and the material supply before implementation, obtains the target recommendation plan, and compensates and updates the process parameters during implementation, thereby improving the energy efficiency of corrugated paperboard packaging production.

Description

Technical Field

[0001] The present invention relates to the technical field of corrugated paper box production and manufacturing, and in particular to an intelligent recommendation method and system for a corrugated paper box packaging production process. Background Art

[0002] Corrugated paper boxes are widely used and are needed in the current logistics and commodity packaging process. The selection of corrugated paper box packaging production process is currently still based on manual experience. When manufacturers receive customer orders, due to the lack of systematic customer demand analysis, it is difficult to accurately match the customer's specific needs with the optimal production process, resulting in a low degree of customization. In addition, during the production process, due to the continuous changes in external factors such as the production environment, raw material supply, and cost structure, the existing process selection methods often lack immediate response and adjustment strategies to these dynamic changes, making the selected process may not be the best in the long run, which in turn leads to the current corrugated paper box packaging production energy efficiency is not ideal. Summary of the invention

[0003] In order to solve at least one of the technical problems mentioned above, the present invention provides an intelligent recommendation method and system for a corrugated box packaging production process.

[0004] In a first aspect, the present invention provides an intelligent recommendation method for a corrugated box packaging production process, the method comprising:

[0005] Obtaining target customer order feature data, inputting the order feature data into a multi-objective optimization model, and obtaining an initial recommendation for a corrugated box packaging production process; the order feature data includes customer identity information, customer demand information, and historical order evaluation information;

[0006] Evaluate a first matching degree between the planned production cycle and the customer demand schedule in the initial recommendation plan, and determine whether the first matching degree is greater than a first preset threshold;

[0007] If not, confirm the priority order and dispatchable range of the target customer orders among all task orders, and adjust the priority order of the target customer orders according to the dispatchable range;

[0008] If yes, evaluate the second matching degree of the raw material and equipment supply and the customer demand quantity in the initial recommendation plan. If the second matching degree does not meet the preset conditions, match the associated production process for the initial recommendation plan based on the production process knowledge graph to generate a target recommendation plan;

[0009] Execute the target recommendation plan and configure the initial parameters of the production process according to the target recommendation plan, obtain the actual operating parameters of the production line in real time and draw the change curve of the actual operating parameters, predict the production operation status according to the change curve to determine the parameter compensation factor, and update the initial parameters of the production process according to the parameter compensation factor.

[0010] Preferably, the execution target recommendation scheme further includes:

[0011] Monitor the abnormal operation task nodes in the production line and generate abnormal task combinations based on the abnormal operation task nodes;

[0012] Taking the task node with the longest running time in the abnormal task combination as the target task node, calculating the process load rate of the abnormal task combination, and determining whether the process load rate is greater than a second preset threshold;

[0013] If yes, generate a target scheduling task set according to the target task node, the preceding adjacent task node and the succeeding adjacent task node of the target task node;

[0014] If not, the target task node is used as the target scheduling task.

[0015] Preferably, the calculating the process load rate of the abnormal task combination includes:

[0016]

[0017] In the formula, C J represents the process load rate of abnormal task combination J, c j is the process load rate of target task node j, c j-1 Represents the target task node c j The process load rate of the preceding adjacent task node, c j+1 Represents the target task node c j The process load rate of the subsequent adjacent task nodes.

[0018] Preferably, the method of matching the associated production process for the initial recommendation scheme based on the production process knowledge graph to generate the target recommendation scheme includes:

[0019] In the production process knowledge graph, select several production processes associated with the initial recommended solution, and calculate the degree of relevance between each production process and the initial recommended solution:

[0020]

[0021] In the formula, S xy Indicates the correlation between the x-th production process and the initial recommended solution y, G x 、F x Respectively represent the product output quality and production efficiency of the x-th production process; Gy 、F y They represent the product output quality and production efficiency of the initial recommended solution y respectively; M x 、N x Respectively represent the production cost and material energy consumption of the x-th production process; M y 、N y They represent the production cost and material energy consumption of the initial recommended solution y respectively; α and β represent weights;

[0022] The associated production processes whose correlation degree is greater than a third preset threshold are screened to generate a target recommendation solution.

[0023] In a second aspect, the present invention further provides an intelligent recommendation system for a corrugated box packaging production process, the system comprising:

[0024] An initial recommendation scheme generation module is used to obtain order feature data of target customers, input the order feature data into the multi-objective optimization model, and obtain an initial recommendation scheme for the corrugated box packaging production process; the order feature data includes customer identity information, customer demand information, and historical order evaluation information;

[0025] A target recommendation scheme generating module is used to evaluate a first matching degree between a planned production cycle and a customer demand schedule in an initial recommendation scheme, and determine whether the first matching degree is greater than a first preset threshold;

[0026] If not, confirm the priority order and dispatchable range of the target customer orders among all task orders, and adjust the priority order of the target customer orders according to the dispatchable range;

[0027] If yes, evaluate the second matching degree of the raw material and equipment supply and the customer demand quantity in the initial recommendation plan. If the second matching degree does not meet the preset conditions, match the associated production process for the initial recommendation plan based on the production process knowledge graph to generate a target recommendation plan;

[0028] The process parameter update module is used to execute the target recommendation plan and configure the initial parameters of the production process according to the target recommendation plan, obtain the actual operating parameters of the production line in real time and draw the change curve of the actual operating parameters, predict the production operation status according to the change curve to determine the parameter compensation factor, and update the initial parameters of the production process according to the parameter compensation factor.

[0029] Preferably, the process parameter updating module includes:

[0030] An abnormal task monitoring unit is used to monitor abnormal operation task nodes in the production line and generate abnormal task combinations according to the abnormal operation task nodes;

[0031] The scheduling task generation unit is used to take the task node with the longest running time in the abnormal task combination as the target task node, calculate the process load rate of the abnormal task combination, and determine whether the process load rate is greater than a second preset threshold;

[0032] If yes, generate a target scheduling task set according to the target task node, the preceding adjacent task node and the succeeding adjacent task node of the target task node;

[0033] If not, the target task node is used as the target scheduling task.

[0034] Preferably, the scheduling task generation unit is used to calculate the process load rate of the abnormal task combination, including:

[0035]

[0036] In the formula, C J represents the process load rate of abnormal task combination J, c j is the process load rate of target task node j, c j-1 Represents the target task node c j The process load rate of the preceding adjacent task node, c j+1 Represents the target task node c j The process load rate of the subsequent adjacent task nodes.

[0037] Preferably, the target recommendation scheme generating module is further used for:

[0038] In the production process knowledge graph, select several production processes associated with the initial recommended solution, and calculate the degree of relevance between each production process and the initial recommended solution:

[0039]

[0040] In the formula, S xy Indicates the correlation between the x-th production process and the initial recommended solution y, G x 、F x Respectively represent the product output quality and production efficiency of the x-th production process; G y 、F y They represent the product output quality and production efficiency of the initial recommended solution y respectively; M x 、N x Respectively represent the production cost and material energy consumption of the x-th production process; M y 、N y They represent the production cost and material energy consumption of the initial recommended solution y respectively; a and β represent weights;

[0041] The associated production processes whose correlation degree is greater than a third preset threshold are screened to generate a target recommendation solution.

[0042] In a third aspect, the present invention further provides an electronic device comprising: a processor and a memory, wherein the memory is used to store computer program code, wherein the computer program code comprises computer instructions, and when the processor executes the computer instructions, the electronic device executes the method as described in the first aspect above and any possible implementation thereof.

[0043] In a fourth aspect, the present invention further provides a computer-readable storage medium, wherein a computer program is stored in the computer-readable storage medium, wherein the computer program includes program instructions, and when the program instructions are executed by a processor of an electronic device, the processor executes the method as described in the first aspect above and any possible implementation thereof.

[0044] Compared with the prior art, the present invention has the following beneficial effects:

[0045] 1) The present invention first obtains the order feature data of the target customer, inputs the order feature data into the multi-objective optimization model, and obtains the initial recommendation plan for the corrugated box packaging production process; the order feature data includes customer identity information, customer demand information, and historical order evaluation information. The present invention takes into account customer identity information, customer demand information, and historical order evaluation information, and combines the multi-objective optimization model to minimize cost and optimize quality as optimization goals, and take the raw material supply and equipment operation involved in the production process as constraints, so that the initial recommendation plan can be quickly and accurately output to match customer needs.

[0046] 2) After obtaining the initial recommendation plan, the present invention will evaluate the first matching degree between the planned production cycle and the customer demand progress in the initial recommendation plan, and determine whether the first matching degree is greater than the first preset threshold value; if not, confirm the priority order and schedulable range of the target customer order in all task orders, and adjust the priority order of the target customer order according to the schedulable range; if so, evaluate the second matching degree between the raw material and equipment supply and the customer demand quantity in the initial recommendation plan, and if the second matching degree does not meet the preset conditions, match the associated production process for the initial recommendation plan based on the production process knowledge graph to generate a target recommendation plan. Since the timeliness of the order is more important, when the number of orders from the carton packaging production and supply manufacturer is large and the target customer order is more urgent, the production priority order of the current target customer is adjusted by determining the schedulable range, so that the more urgent orders can be processed first, and the order task execution management work can be better performed. If the order is planned in production time, the present invention further considers the matching degree between the raw materials and equipment in the production process and the order tasks required by the customer. If they cannot be matched, the associated production process is matched from the production process knowledge graph as the initial recommendation plan. In this way, the original plan can be updated through the associated process, which increases the feasibility of the target recommendation plan, thereby ensuring that the order tasks can meet customer needs in terms of timeliness, quality, quantity and other aspects, and enhance customer experience.

[0047] 3) Execute the target recommendation scheme and configure the initial parameters of the production process according to the target recommendation scheme, obtain the actual operating parameters of the production line in real time and draw the change curve of the actual operating parameters, predict the production operation status according to the change curve to determine the parameter compensation factor, and update the initial parameters of the production process according to the parameter compensation factor. When executing the task, due to environmental influences and the actual equipment operation status, the initial parameters of the production process configured under the target recommendation scheme may not be optimal. Therefore, the present invention will take into account the timely response and adjustment strategy of dynamic changes based on the actual operation situation, and update the initial parameters of the production process by calculating the parameter compensation factor to make it more in line with the actual production situation, thereby ensuring that the production process can be carried out stably, improving production efficiency and production quality, and enhancing the energy efficiency of carton packaging production.

[0048] It is to be understood that both the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the disclosure. BRIEF DESCRIPTION OF THE DRAWINGS

[0049] In order to more clearly illustrate the technical solutions in the embodiments of the present invention or the background technology, the drawings required for use in the embodiments of the present invention or the background technology will be described below.

[0050] The drawings herein are incorporated into the specification and constitute a part of the specification. These drawings illustrate embodiments consistent with the present disclosure and are used to illustrate the technical solutions of the present disclosure together with the specification.

[0051] Figure 1 A schematic diagram of a process flow of an intelligent recommendation method for a corrugated paper box packaging production process provided by an embodiment of the present invention;

[0052] Figure 2 A schematic diagram of the structure of an intelligent recommendation system for a corrugated paper box packaging production process provided by an embodiment of the present invention;

[0053] Figure 3 The embodiment of the present invention provides Figure 2 Schematic diagram of the structure of the subunits of the process parameter updating module 300. DETAILED DESCRIPTION

[0054] In order to enable those skilled in the art to better understand the scheme of the present invention, the technical scheme in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0055] The terms "first", "second", etc. in the specification and claims of the present invention and the above-mentioned drawings are used to distinguish different objects, rather than to describe a specific order. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions. For example, a process, method, system, product or device that includes a series of steps or units is not limited to the listed steps or units, but may optionally include steps or units that are not listed, or may optionally include other steps or units that are inherent to these processes, methods, products or devices.

[0056] The term "and / or" herein is only a description of the association relationship of the associated objects, indicating that there may be three relationships. For example, A and / or B can represent: A exists alone, A and B exist at the same time, and B exists alone. In addition, the term "at least one" herein represents any combination of at least two of any one or more of a plurality of. For example, including at least one of A, B, and C can represent including any one or more elements selected from the set consisting of A, B, and C.

[0057] Reference to "embodiments" herein means that a particular feature, structure, or characteristic described in conjunction with the embodiments may be included in at least one embodiment of the present invention. The appearance of the phrase in various places in the specification does not necessarily refer to the same embodiment, nor is it an independent or alternative embodiment that is mutually exclusive with other embodiments. It is explicitly and implicitly understood by those skilled in the art that the embodiments described herein may be combined with other embodiments.

[0058] In addition, in order to better illustrate the present invention, numerous specific details are provided in the following specific embodiments. It should be understood by those skilled in the art that the present invention can be implemented without certain specific details. In some examples, methods, means, components and circuits well known to those skilled in the art are not described in detail in order to highlight the subject matter of the present invention.

[0059] At present, the production process selection for corrugated boxes mostly relies on manual experience and lacks a dynamic adjustment mechanism, which leads to production efficiency and processing quality that are not as expected and cannot meet customer needs. To this end, the present invention provides an intelligent recommendation method for corrugated box packaging production process, which can quickly generate an initial recommendation plan based on a multi-objective optimization model, and conduct a feasibility assessment on the plan through production cycle and material supply to change the order task execution priority and match the associated process, thereby obtaining an optimized target recommendation plan. In the process of production, the dynamic influence mechanism is considered to compensate and optimize the process parameters to make them more in line with the actual situation, greatly speed up production efficiency while ensuring production quality, enhance production management efficiency, and further meet customer needs.

[0060] See also Figure 1 , Figure 1 The present invention provides a flow chart of an intelligent recommendation method for a corrugated paper box packaging production process. Figure 1 As shown, the method comprises the following steps:

[0061] S10, obtaining order feature data of target customers, inputting the order feature data into a multi-objective optimization model, and obtaining an initial recommendation plan for the corrugated carton packaging production process; the order feature data includes customer identity information, customer demand information, and historical order evaluation information;

[0062] S20, evaluating the first matching degree between the planned production cycle and the customer demand progress in the initial recommendation plan, and determining whether the first matching degree is greater than a first preset threshold; if not, executing step S201 first and then executing step S202; if so, directly executing step S202.

[0063] S201, confirming the priority order and dispatchable range of the target customer orders among all task orders, and adjusting the priority order of the target customer orders according to the dispatchable range;

[0064] S202, evaluating the second matching degree of the raw material and equipment supply and the customer demand quantity in the initial recommendation plan, if the second matching degree does not meet the preset condition, matching the associated production process for the initial recommendation plan based on the production process knowledge graph, and generating a target recommendation plan;

[0065] S30, execute the target recommendation plan and configure the initial parameters of the production process according to the target recommendation plan, obtain the actual operating parameters of the production line in real time and draw a change curve of the actual operating parameters, predict the production operation status according to the change curve to determine the parameter compensation factor, and update the initial parameters of the production process according to the parameter compensation factor.

[0066] In this embodiment, first step S10 is to obtain an initial recommendation scheme based on the customer order feature data. The order feature data mainly includes customer identity information, customer demand information and historical order evaluation information. Customer identity information mainly refers to the historical transaction situation between the customer and the manufacturer, the industry to which the customer belongs, the geographical location, the application scale and other basic information, which is used to understand the specific demand background of the customer. The historical transaction situation can be used to determine whether the customer is the first transaction with the manufacturer. If it is an old customer with a historical transaction, the transaction record can be called to obtain the customer's historical order needs and habits, so as to provide a reference for this production process recommendation. Customer demand information is used to record in detail the customer's specific requirements for corrugated boxes, including size, load-bearing capacity, bursting strength, printing requirements, environmental protection standards, delivery time, etc. The historical order evaluation information collects customer feedback on previous orders, such as satisfaction scores, specific comments, such as evaluations on packaging strength, appearance, cost-effectiveness, and return rates, etc., to evaluate the overall applicability of past production processes.

[0067] After the order feature data is obtained, the order feature data is input into the multi-objective optimization model to obtain the initial recommendation plan for the corrugated box packaging production process. Specifically, in order to improve the quality of the output recommendation plan, this embodiment will first clean the collected order feature data, including processing missing values ​​and outliers, and can also construct derivative features to enrich the diversity of the data, such as calculating the weighted scores of customers' packaging strength and cost sensitivity based on historical order evaluation information. After data preprocessing, the optimization model is constructed as follows:

[0068] 1) Define objective function: Based on customer needs, determine multiple objective functions, which can usually be minimizing costs, maximizing packaging strength, maximizing customer satisfaction, etc. Each objective function represents an optimization goal.

[0069] 2) Selection algorithm: Use multi-objective optimization algorithms, such as genetic algorithms, particle swarm optimization, etc. These algorithms can find the optimal solution set among multiple conflicting objectives.

[0070] 3) Constraint setting: According to production capacity and technical limitations, set constraints, such as maximum production cycle, material availability, equipment operating parameter specifications, etc.

[0071] When the model has multiple optimization objectives, the model will output a set of optimal solutions for the objective function of each optimization objective, thereby generating multiple recommendation plans, and then an initial recommendation plan can be finally screened out based on customer preferences.

[0072] Therefore, this embodiment takes into account customer identity information, customer demand information and historical order evaluation information, and combines it with a multi-objective optimization model. It can use minimum cost and optimal quality as optimization goals, and use the raw material supply and equipment operation involved in the production process as constraints, so that the initial recommendation plan can be output quickly and accurately. Compared with the production process selected by manual experience, the process recommendation plan obtained by this optimization screening method can better match customer needs, making the early planning of production tasks more reasonable, thereby improving the efficiency of order management.

[0073] Furthermore, step S20 is mainly to conduct a feasibility assessment on the initial recommendation plan output by the model. First, due to the large number of orders from manufacturers, when the orders from target customers are obtained and the recommended production processes are obtained based on the needs of the target customers, it is necessary to first evaluate the time for executing the order tasks. Specifically, the first matching degree between the planned production cycle in the initial recommendation plan and the customer demand progress is evaluated, and it is determined whether the first matching degree is greater than a first preset threshold. If not, first execute step S201 and then execute step S202; if so, directly execute step S202.

[0074] In one embodiment, the first matching degree between the planned production cycle and the customer demand schedule in the initial recommendation solution is evaluated as follows:

[0075] 1) Calculate the delivery date deviation rate. This value is the difference between the planned completion date in the initial recommendation and the customer demand date, and then divided by the customer demand date. This value measures the ratio of the gap between the planned completion date and the customer demand date to the customer demand date. The smaller the value, the higher the matching degree.

[0076] 2) Calculate the on-time delivery index: You can pre-set a reasonable buffer time as a tolerance space, and then divide the difference between the planned completion date in the initial recommendation plan and the customer demand date by the buffer time. The closer the value is to 1, the higher the matching degree is, that is, the order task can be delivered within the buffer time.

[0077] After obtaining the delivery date deviation rate and the on-time delivery index, the weights of the two parameters can be set respectively, such as 0.5 for both, and then the first matching degree is calculated by weighted sum. It can be understood that 0.5 is only a preferred real-time method, and the weight value can be flexibly adjusted as needed in specific scenarios, which is not limited here.

[0078] On the one hand, after the first matching degree is calculated, if the value is less than or equal to the first preset threshold, it means that the execution production time of the order cannot meet the customer's needs. Therefore, the priority order and schedulable range of the target customer's order in all task orders will be confirmed at this time, and the priority order of the target customer's order will be adjusted according to the schedulable range. The schedulable range can first lock the orders whose execution order is before the current target customer's order, and determine whether these orders can be swapped with the order of the target customer's order. For example, customer A places an order first, and the execution order is before customer B, but customer B is more urgent in terms of delivery time, so customer B's order task can be placed before customer A to complete the order task execution management scheduling.

[0079] On the other hand, if the first matching degree is greater than the first preset threshold, it means that the cycle planning of the target customer order in the initial recommendation plan can meet the customer demand progress. In this case, it is necessary to further determine whether the second matching degree of the raw material and equipment supply and the customer demand quantity in the initial recommendation plan can meet the preset conditions. It can be understood that the equipment, equipment parameters, execution order of production process links, product quantity, and structural quality of processed finished products used in different production processes are different. If the raw materials or equipment process of a process is insufficient, an alternative solution can be found to ensure that the construction period will not be delayed. The second matching degree mainly refers to the matching degree of raw material and equipment supply and customer demand quantity. For example, customer A needs to produce 50 corrugated boxes, and there are 3 equipments that need to run at the same time, but one of the equipments has aged under this process. In order not to affect production efficiency and quality, it can be considered to call a device from the replacement line that produces other products, or consider how to adjust the production operation data under 2 equipments to ensure production efficiency and quality. Therefore, step S202 aims to match the associated production process for the initial recommendation plan from the production process knowledge map. Among them, the production process knowledge graph is a knowledge system that organizes and represents entities such as production processes, equipment, raw materials, process parameters, quality control, troubleshooting, and their interrelationships in a graphical way. It uses graph databases or similar structures to store and manage knowledge, making information more structured and associated, and easy to query, analyze, and reason. Usually, a knowledge graph is established in advance in the production and manufacturing database of corrugated boxes, with various entities in the production process (such as production equipment, types of raw materials, process steps, etc.) as nodes, and the connections between entities (such as raw material usage, equipment operation sequence, process parameter influence, etc.) as edges, forming a huge knowledge network. When you need to match an associated process, you only need to find a solution to the current problem or an associated process that can replace the current process from the graph.

[0080] In one embodiment, matching the associated production process to the initial recommendation solution based on the production process knowledge graph to generate the target recommendation solution includes:

[0081] In the production process knowledge graph, select several production processes associated with the initial recommended solution, and calculate the degree of relevance between each production process and the initial recommended solution:

[0082]

[0083] In the formula, S xy Indicates the correlation between the x-th production process and the initial recommended solution y, G x 、F x Respectively represent the product output quality and production efficiency of the x-th production process; G y 、F yThey represent the product output quality and production efficiency of the initial recommended solution y respectively; M x 、N x Respectively represent the production cost and material energy consumption of the x-th production process; M y 、N y They represent the production cost and material energy consumption of the initial recommended solution y respectively; a and β represent weights;

[0084] The associated production processes whose correlation degree is greater than a third preset threshold are screened to generate a target recommendation solution.

[0085] When matching associated solutions, this embodiment takes into account the correlation among output quality, raw tea efficiency, production cost and material energy consumption to match associated production processes with a higher degree of correlation, thereby adjusting the initial recommended solution to ensure that the initial solution can proceed smoothly.

[0086] Therefore, this embodiment can evaluate the feasibility of the initial recommendation plan from two perspectives: timeliness and production raw material process. Since the timeliness of the order is more important, when the number of orders from the carton packaging production and supply manufacturer is large and the target customer order is more urgent, the production priority order of the current target customer is adjusted by determining the schedulable range, so that the more urgent orders can be processed first, and the order task execution management work can be better performed. After the order is planned in production time, further consider the matching degree between the raw materials and equipment in the production process and the customer's required order tasks. If they cannot be matched, consider matching the associated production process from the production process knowledge graph for the initial recommendation plan. In this way, the original plan can be updated through the associated process, which increases the feasibility of the target recommendation plan, thereby ensuring that the order task can meet customer needs in terms of timeliness, quality, quantity and other aspects, and enhance customer experience.

[0087] When executing a task, due to environmental influences and the actual equipment operating status, the initial production process parameters configured under the target recommendation scheme may not be optimal. Therefore, it is necessary to execute the target recommendation scheme in step S30. First, the initial production process parameters are configured according to the target recommendation scheme, the actual operating parameters of the production line are obtained in real time, and a change curve of the actual operating parameters is drawn. The production operating status is predicted based on the change curve to determine the parameter compensation factor, and the initial production process parameters are updated based on the parameter compensation factor.

[0088] Specifically, when determining the parameter compensation factor, firstly, various operating parameters, including temperature, pressure, printing speed, etc., are detected in real time according to the sensors deployed on the production line, and then input into the data analysis system. Taking temperature as an example, assuming that the temperature of the production equipment will become higher and higher during the operation process, the temperature parameters within a short period can be collected first, and then the temperature change curve can be drawn. The operating status of the equipment is predicted based on the temperature change curve of the equipment. When predicting the operating status, the clustering algorithm can be mainly used, and the current temperature change curve and the temperature change curve in the historical operation process are used as the model input. After clustering, the clustering cluster where the current temperature change curve is located can be obtained. As long as the production operation status of the historical temperature change curve is found from the clustering cluster, it can be output as the prediction result.

[0089] Furthermore, when the predicted production operation status is obtained, different parameter compensation strategies can be designed. For example, when it is predicted that the equipment is about to overheat, the system parameters may need to be adjusted. If you want to compensate for the decrease in production efficiency caused by temperature changes, you can use the temperature compensation formula:

[0090] k c =k0(1+γ(T g -T s ))

[0091] In the formula, k0 is the initial parameter of the production process, k c is the process parameter after compensation, T g 、T s are the target temperature and actual temperature respectively, and γ is the compensation coefficient determined according to the characteristics of the equipment.

[0092] In summary, this embodiment takes into account the timely response and adjustment strategies of dynamic changes based on the actual operating conditions, and updates the initial parameters of the production process by calculating the parameter compensation factor to make it more in line with the actual production situation, thereby ensuring that the production process can proceed stably, improving production efficiency and quality, and enhancing the energy efficiency of carton packaging production.

[0093] In one embodiment, the execution target recommendation scheme further includes:

[0094] Monitor the abnormal operation task nodes in the production line and generate abnormal task combinations based on the abnormal operation task nodes;

[0095] Taking the task node with the longest running time in the abnormal task combination as the target task node, calculating the process load rate of the abnormal task combination, and determining whether the process load rate is greater than a second preset threshold;

[0096] If yes, generate a target scheduling task set according to the target task node, the preceding adjacent task node and the succeeding adjacent task node of the target task node;

[0097] If not, the target task node is used as the target scheduling task.

[0098] Preferably, the process load rate of the calculation abnormal task combination includes:

[0099]

[0100] In the formula, C J represents the process load rate of abnormal task combination J, c j is the process load rate of target task node j, c j-1 Represents the target task node c j The process load rate of the preceding adjacent task node, c j+1 Represents the target task node c j The process load rate of the subsequent adjacent task nodes.

[0101] Usually, in the actual operation process, a certain link may be abnormal, thus affecting the entire production line task. For this reason, this embodiment aims to perform abnormal monitoring and schedule abnormal tasks to ensure the stability of production efficiency and quality. Specifically, an abnormal operation task node mainly refers to a node with a long operation time or a node where obvious problems with production quality are detected: for example, a link C is stuck, which will affect the normal operation of subsequent links, or obvious printing errors are detected in the printing link, then these links can be regarded as abnormal operation task nodes.

[0102] When the abnormal running task node is obtained, the abnormal task combination is first generated, and then the task node with the longest running time is selected as the target task node. Based on the target task node, the process load rate of the abnormal task combination is calculated.

[0103] The process load rate is mainly determined by the adjacent preceding tasks and subsequent adjacent tasks of the target task node. The process load rate usually refers to the ratio of the actual use of the production equipment within a specific time to its maximum production capacity. After the process load rate is calculated, it is compared with the second preset threshold. If it is greater than the second preset threshold, it means that the process load rate is too high. At this time, the target task node, the preceding adjacent task node of the target task node, and the subsequent adjacent task node will generate a target scheduling task set, and these tasks will be scheduled. If it is less than or equal to the second preset threshold, the target task node only needs to be scheduled as a target scheduling task, which can reduce the production difficulty of the production line and ensure production efficiency.

[0104] Therefore, this embodiment monitors abnormal task running nodes, takes into account the process load rate and determines appropriate target scheduling tasks. It can perform reasonable scheduling when the production line load is heavy, thereby speeding up the production line efficiency and improving production quality, ensuring the stable operation of the production line.

[0105] See also Figure 2 In one embodiment, the present invention further provides an intelligent recommendation system for a corrugated box packaging production process, the system comprising:

[0106] The initial recommendation scheme generating module 100 is used to obtain the order feature data of the target customer, input the order feature data into the multi-objective optimization model, and obtain the initial recommendation scheme of the corrugated box packaging production process; the order feature data includes customer identity information, customer demand information and historical order evaluation information;

[0107] The target recommendation scheme generating module 200 is used to evaluate the first matching degree between the planned production cycle and the customer demand progress in the initial recommendation scheme, and determine whether the first matching degree is greater than a first preset threshold;

[0108] If not, confirm the priority order and dispatchable range of the target customer orders among all task orders, and adjust the priority order of the target customer orders according to the dispatchable range;

[0109] If yes, evaluate the second matching degree of the raw material and equipment supply and the customer demand quantity in the initial recommendation plan. If the second matching degree does not meet the preset conditions, match the associated production process for the initial recommendation plan based on the production process knowledge graph to generate a target recommendation plan;

[0110] The process parameter updating module 300 is used to execute the target recommendation scheme and configure the initial parameters of the production process according to the target recommendation scheme, obtain the actual operating parameters of the production line in real time and draw a change curve of the actual operating parameters, predict the production operation status according to the change curve to determine the parameter compensation factor, and update the initial parameters of the production process according to the parameter compensation factor.

[0111] See also Figure 3 In one embodiment, the process parameter updating module 300 includes:

[0112] The abnormal task monitoring unit 301 is used to monitor the abnormal operation task nodes in the production line and generate abnormal task combinations according to the abnormal operation task nodes;

[0113] The scheduling task generation unit 302 is used to take the task node with the longest running time in the abnormal task combination as the target task node, calculate the process load rate of the abnormal task combination, and determine whether the process load rate is greater than a second preset threshold;

[0114] If yes, generate a target scheduling task set according to the target task node, the preceding adjacent task node and the succeeding adjacent task node of the target task node;

[0115] If not, the target task node is used as the target scheduling task.

[0116] In one embodiment, the scheduling task generation unit 302 is used to calculate the process load rate of the abnormal task combination, including:

[0117]

[0118] In the formula, C J represents the process load rate of abnormal task combination J, c j is the process load rate of target task node j, c j*1 Represents the target task node c j The process load rate of the preceding adjacent task node, c j+1 Represents the target task node c j The process load rate of the subsequent adjacent task nodes.

[0119] In one embodiment, the target recommendation scheme generating module 200 is further used to:

[0120] In the production process knowledge graph, select several production processes associated with the initial recommended solution, and calculate the degree of relevance between each production process and the initial recommended solution:

[0121]

[0122] In the formula, S xy Indicates the correlation between the x-th production process and the initial recommended solution y, G x 、F x Respectively represent the product output quality and production efficiency of the x-th production process; G y 、F y They represent the product output quality and production efficiency of the initial recommended solution y respectively; M x 、N x Respectively represent the production cost and material energy consumption of the x-th production process; M y 、N y They represent the production cost and material energy consumption of the initial recommended solution y respectively; a and β represent weights;

[0123] The associated production processes whose correlation degree is greater than a third preset threshold are screened to generate a target recommendation solution.

[0124] It can be understood that the functions or modules included in the system provided in this embodiment can be used to execute the method described in the above method embodiment. Its specific implementation can refer to the description of the above method embodiment. For the sake of brevity, it will not be repeated here.

[0125] The present invention also provides an electronic device, including a processor and a memory, wherein the memory is used to store computer program code, and the computer program code includes computer instructions. When the processor executes the computer instructions, the electronic device executes a method as described in any possible implementation manner.

[0126] The present invention also provides a computer-readable storage medium, in which a computer program is stored. The computer program includes program instructions. When the program instructions are executed by a processor of an electronic device, the processor executes a method as described in any possible implementation manner.

[0127] Those skilled in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of the present invention.

[0128] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the aforementioned method embodiments, and will not be repeated here. Those skilled in the art can also clearly understand that the descriptions of the various embodiments of the present invention have different focuses. For the convenience and brevity of description, the same or similar parts may not be repeated in different embodiments. Therefore, for parts not described or not described in detail in a certain embodiment, refer to the records of other embodiments.

[0129] In the several embodiments provided by the present invention, it should be understood that the disclosed systems, devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic. For example, the division of the units is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0130] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0131] In the above embodiments, it can be implemented in whole or in part by software, hardware, firmware or any combination thereof. When implemented by software, it can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on a computer, the process or function described in the embodiment of the present invention is generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions can be stored in a computer-readable storage medium or transmitted through the computer-readable storage medium. The computer instructions can be transmitted from a website site, computer, server or data center to another website site, computer, server or data center by wired (e.g., coaxial cable, optical fiber, digital subscriber line (digital subscriber line, DSL)) or wireless (e.g., infrared, wireless, microwave, etc.) mode. The computer-readable storage medium can be any available medium that can be accessed by a computer or a data storage device such as a server or data center that includes one or more available media integrated. The available medium may be a magnetic medium (eg, a floppy disk, a hard disk, a magnetic tape), an optical medium (eg, a digital versatile disc (DVD)), or a semiconductor medium (eg, a solid state disk (SSD)).

[0132] A person skilled in the art can understand that to implement all or part of the processes in the above-mentioned embodiments, the processes can be completed by a computer program to instruct the relevant hardware, and the program can be stored in a computer-readable storage medium. When the program is executed, it can include the processes of the above-mentioned method embodiments. The aforementioned storage medium includes: a read-only memory (ROM) or a random access memory (RAM), a magnetic disk or an optical disk, and other media that can store program codes.

Claims

1. An intelligent recommendation method for corrugated carton packaging production process, characterized in that: The method comprises: Obtaining target customer order feature data, inputting the order feature data into a multi-objective optimization model, and obtaining an initial recommendation for a corrugated box packaging production process; the order feature data includes customer identity information, customer demand information, and historical order evaluation information; Evaluate a first matching degree between the planned production cycle and the customer demand schedule in the initial recommendation plan, and determine whether the first matching degree is greater than a first preset threshold; If not, confirm the priority order and dispatchable range of the target customer orders among all task orders, and adjust the priority order of the target customer orders according to the dispatchable range; If yes, evaluate the second matching degree of the raw material and equipment supply and the customer demand quantity in the initial recommendation plan. If the second matching degree does not meet the preset conditions, match the associated production process for the initial recommendation plan based on the production process knowledge graph to generate a target recommendation plan; Execute the target recommendation plan and configure the initial parameters of the production process according to the target recommendation plan, obtain the actual operating parameters of the production line in real time and draw the change curve of the actual operating parameters, predict the production operation status according to the change curve to determine the parameter compensation factor, and update the initial parameters of the production process according to the parameter compensation factor; The execution target recommendation scheme further includes: Monitor the abnormal operation task nodes in the production line and generate abnormal task combinations based on the abnormal operation task nodes; Taking the task node with the longest running time in the abnormal task combination as the target task node, calculating the process load rate of the abnormal task combination, and determining whether the process load rate is greater than a second preset threshold; If yes, generate a target scheduling task set according to the target task node, the preceding adjacent task node and the succeeding adjacent task node of the target task node; If not, the target task node is used as the target scheduling task; The process load rate of calculating the abnormal task combination includes: ; In the formula, Indicates abnormal task combination The process load rate, Target task node The process load rate, Indicates the target task node The process load rate of the preceding adjacent task node, Indicates the target task node The process load rate of the subsequent adjacent task nodes; The method of matching the associated production process for the initial recommendation scheme based on the production process knowledge graph to generate the target recommendation scheme includes: In the production process knowledge graph, select several production processes associated with the initial recommended solution, and calculate the degree of relevance between each production process and the initial recommended solution: ; In the formula, Indicates Production process and initial recommendation The degree of relevance, , Respectively represent Product output quality and production efficiency of each production process; , Represents the initial recommended solutions Product output quality and production efficiency; , Respectively represent Production costs and material energy consumption of each production process; , Represents the initial recommended solutions production costs and material energy consumption; represents weight; Associated production processes with a correlation degree greater than a third preset threshold are screened to generate a target recommendation solution.

2. An intelligent recommendation system for corrugated carton packaging production process, characterized in that: The system comprises: An initial recommendation scheme generation module is used to obtain order feature data of target customers, input the order feature data into the multi-objective optimization model, and obtain an initial recommendation scheme for the corrugated box packaging production process; the order feature data includes customer identity information, customer demand information, and historical order evaluation information; A target recommendation scheme generating module is used to evaluate a first matching degree between a planned production cycle and a customer demand schedule in an initial recommendation scheme, and determine whether the first matching degree is greater than a first preset threshold; If not, confirm the priority order and dispatchable range of the target customer orders among all task orders, and adjust the priority order of the target customer orders according to the dispatchable range; If yes, evaluate the second matching degree of the raw material and equipment supply and the customer demand quantity in the initial recommendation plan. If the second matching degree does not meet the preset conditions, match the associated production process for the initial recommendation plan based on the production process knowledge graph to generate a target recommendation plan; The process parameter update module is used to execute the target recommendation scheme and configure the initial parameters of the production process according to the target recommendation scheme, obtain the actual operating parameters of the production line in real time and draw the change curve of the actual operating parameters, predict the production operation status according to the change curve to determine the parameter compensation factor, and update the initial parameters of the production process according to the parameter compensation factor; The process parameter updating module comprises: An abnormal task monitoring unit is used to monitor abnormal operation task nodes in the production line and generate abnormal task combinations according to the abnormal operation task nodes; The scheduling task generation unit is used to take the task node with the longest running time in the abnormal task combination as the target task node, calculate the process load rate of the abnormal task combination, and determine whether the process load rate is greater than a second preset threshold; If yes, generate a target scheduling task set according to the target task node, the preceding adjacent task node and the succeeding adjacent task node of the target task node; If not, the target task node is used as the target scheduling task; The scheduling task generation unit is used to calculate the process load rate of the abnormal task combination, including: ； In the formula, Indicates abnormal task combination The process load rate, Target task node The process load rate, Indicates the target task node The process load rate of the preceding adjacent task node, Indicates the target task node The process load rate of the subsequent adjacent task nodes; The target recommendation scheme generating module is further used for: In the production process knowledge graph, select several production processes associated with the initial recommended solution, and calculate the degree of relevance between each production process and the initial recommended solution: ； In the formula, Indicates Production process and initial recommendation The degree of relevance, , Respectively represent Product output quality and production efficiency of each production process; , Represents the initial recommended solutions Product output quality and production efficiency; , Respectively represent Production costs and material energy consumption of each production process; , Represents the initial recommended solutions production costs and material energy consumption; represents weight; The associated production processes whose correlation degree is greater than a third preset threshold are screened to generate a target recommendation solution.

3. An electronic device, characterized in that: include: A processor and a memory, wherein the memory is used to store computer program codes, wherein the computer program codes include computer instructions. When the processor executes the computer instructions, the electronic device executes the intelligent recommendation method for the corrugated box packaging production process as described in claim 1.

4. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, which includes program instructions. When the program instructions are executed by a processor of an electronic device, the processor executes the intelligent recommendation method for the corrugated box packaging production process according to claim 1.

Images