Intelligent carton production management system and method

Abstract

The invention discloses an intelligent carton production management system and method, and relates to the technical field of packaging box production management, the system comprises a production management module, a tracking module, a recovery module and a data analysis module, the production management module is used for arranging a production plan according to an order after receiving the order; the tracking module is used for identifying a carton through Internet equipment and monitoring and collecting the position and state information of the carton in real time, and the output end of the tracking module is electrically connected with the input end of the recycling module; the recovery module is used for receiving a recovery request and arranging a recovery task, and the output end of the recovery module is electrically connected with the input end of the data analysis module; the data analysis module is used for storing and analyzing carton full life cycle data and optimizing a production plan and a recovery strategy; according to the intelligent carton production management system and method, full-process intelligent management of carton production, use and recovery is achieved, and the management efficiency is improved through model and formula optimization of all the modules.

Description

Technical Field

[0001] This application relates to the field of packaging box production management technology, and more specifically, to an intelligent carton production management system and method. Background Technology

[0002] Currently, with the rapid development of e-commerce and logistics, the demand for cardboard boxes as a major packaging material has increased dramatically. However, the production, use, and recycling of cardboard boxes suffer from problems such as resource waste and low management efficiency. Traditional cardboard box production management mainly relies on manual recording and scheduling, lacking systematic tracking methods, resulting in low recycling rates and inefficient reuse of cardboard boxes.

[0003] Therefore, an intelligent cardboard box production management system and method are proposed to address the aforementioned technical issues. Summary of the Invention

[0004] In order to overcome the above-mentioned defects of the prior art, this application provides an intelligent carton production management system and method to solve the problems mentioned in the background art.

[0005] On the one hand, to achieve the above objectives, this application provides the following technical solution: an intelligent cardboard box production management system, including a production management module, a tracking module, a recycling module, and a data analysis module. The production management module is used to arrange a production plan according to the order after receiving the order, and the output of the production management module is electrically connected to the input of the tracking module; The tracking module is used to identify and monitor the location and status information of the cardboard boxes in real time through Internet devices, and the output of the tracking module is electrically connected to the input of the recycling module. The recycling module is used to receive recycling requests and arrange recycling tasks, and the output end of the recycling module is electrically connected to the input end of the data analysis module. The data analysis module is used to store and analyze data throughout the entire lifecycle of cardboard boxes, and to optimize production plans and recycling strategies.

[0006] By adopting the above technical solutions, the production of cardboard boxes can be managed efficiently, enabling precise tracking and scheduling of cardboard boxes, improving the recycling rate of cardboard boxes, and allowing cardboard boxes to be reused multiple times.

[0007] Preferably, the production management module includes an order management unit and a production scheduling unit. The order management unit is used to construct an order priority evaluation model. After receiving an order, the order priority evaluation model is used to determine the order processing order by comprehensively considering the order's urgency, batch size, and customer weight. The order priority calculation formula in the order priority evaluation model is: Among them, P i Let D be the priority of order i.i For the delivery date of order i, T c Q is the current time. i Let Q be the quantity of order i. max C is the maximum number of orders set by the system. i The customer weighting coefficient is determined by the enterprise based on the customer's historical purchase amount, cooperation period and credit rating. w1, w2 and w3 are weighting factors, and w1+w2+w3=1.

[0008] By adopting the above technical solutions, we can ensure that orders nearing their delivery date are processed with priority, avoid customer complaints or penalties due to overdue orders, allocate higher priority to high-value customers, ensure that their orders are produced first, enhance customer loyalty, and ensure that high-priority orders are allocated equipment and materials first.

[0009] Preferably, the production scheduling unit is used to establish a production scheduling model based on constraint theory, with the goal of minimizing the production cycle. It formulates a production plan based on equipment capacity and material constraints. Specifically, the production scheduling model is: minT = max{B j}, j=1,2,...,m, the process sequence constraint is: B i ≥B k +t ik Equipment capacity constraints are: Material requirement constraint is: S i ≥R i ; Where T is the total production cycle, B j Let m be the completion time of equipment j, m be the number of equipment, and B be the completion time of equipment j. i B k The completion times of processes i and k are respectively, t ik x is the preparation time from process i to process k. ij B is the time for equipment j to process process i. apj S represents the available capacity of equipment j. i R is the material supply quantity for process i. i Let n be the material requirement for process i, and n be the number of processes.

[0010] By adopting the above technical solutions and utilizing the production scheduling model built upon constraint theory, key conditions such as equipment capacity and material constraints are fully considered. With the goal of minimizing the production cycle, this model provides strong support for enterprises to formulate scientific and reasonable production scheduling plans. In practical applications, enterprises can optimize and adjust the parameters in the model based on their own production characteristics and actual data, thereby maximizing production efficiency and enhancing their competitiveness in the market.

[0011] Preferably, the tracking module includes an identification unit and a monitoring unit. The identification unit assigns a unique electronic identification code to each carton using an RFID or NFC tag. The monitoring unit is used to construct a real-time status monitoring model based on the Internet of Things (IoT). It calculates the turnover efficiency and anomaly probability of the cartons using data collected by the device and uploads the obtained data to the data analysis module. In the real-time status monitoring model, the electronic identification code on the carton is read by an IoT device, and the read electronic identification code information is then transmitted to the monitoring unit. The turnover efficiency calculation formula in the real-time status monitoring model is: Where E is the carton turnover efficiency, L is the actual turnover distance of the carton, and T is the total turnover distance. f The preset standard turnaround time is η, which is the environmental interference coefficient and its value ranges from [0.8 to 1.2].

[0012] Preferably, the formula for calculating the anomaly probability in the real-time status monitoring model is: Among them, P a Let X be the probability of an abnormal state of the cardboard box, X be a vector of multiple state parameters including position offset, vibration frequency, temperature and humidity, and α and β be model parameters, which are determined by training with historical data.

[0013] By adopting the above technical solutions, low-cost RFID or NFC tags are used to reduce the tracking cost of cartons. RFID or NFC tags support batch reading within 10 meters, improving the scanning efficiency of a single carton and adapting to high-speed sorting scenarios in logistics hubs. Each tag has a unique built-in ID that can store basic information about the carton (production batch, specifications), enabling rapid traceability without relying on external databases. Production capacity allocation can be adjusted based on turnover efficiency data (such as prioritizing the production of high-turnover cartons), improving equipment utilization. By predicting the integrity rate of cartons through anomaly probability, the recycling priority can be dynamically adjusted to improve the recycling rate.

[0014] Preferably, the recycling module includes a recycling request unit and a recycling scheduling unit. The recycling request unit is used to design a recycling demand prediction model, combining historical recycling data, peak season patterns in logistics, and regional economic indicators to predict the recycling demand in each region. The recycling demand prediction model is specifically as follows: Among them, F r Let X be the regional recycling demand, a0 be a constant term, and X be the recycling demand. i For characteristics related to historical recovery volume, Y j For logistics cycle characteristics, Z m As a characteristic of regional economy, a i b j c m Here, ε is the regression coefficient, and ε is the random error term. φ and ψ represent the corresponding number of features.

[0015] Preferably, the recycling scheduling unit is used to construct a recycling path optimization model based on an improved genetic algorithm, which comprehensively considers recycling cost, time window, and cardboard box integrity rate to schedule the recycling of cardboard boxes, and the recycling path optimization model is set with a recycling path optimization objective function as follows: The constraints are: x ij ∈{0,1}; where C is the total recovery cost, d ij x is the distance from recycling point i to recycling point j; ij For decision variables, 1 indicates from i to j, 0 otherwise; h i Let t be the time penalty coefficient for recycling point i. i e represents the actual arrival time. i p is the deadline for the time window; i w′ is the value coefficient of the cardboard boxes at recycling point i. i n represents the cardboard box integrity rate; n′ represents the number of recycling points.

[0016] By adopting the above technical solutions and fusing multi-dimensional features, the accuracy of prediction is improved. By linking the recycling demand output by the prediction model with the production plan, the production end automatically adjusts the supply of new cardboard boxes in the region, and intelligently regulates the production efficiency of cardboard boxes.

[0017] Preferably, the data analysis module includes a data storage unit and an analysis unit. The data storage unit adopts a distributed storage structure to store the entire lifecycle data of the cardboard box. The analysis unit is used to construct a deep learning-based lifecycle optimization model. The lifecycle optimization model is trained with multi-dimensional data to optimize production plans and recycling strategies. Specifically, the lifecycle optimization model is: minJ = λ1L p +λ2L r +λ3L e Where J is the comprehensive optimization objective function; L p The loss function in the production process reflects production efficiency and cost; L r The loss function for the recycling process reflects the recycling efficiency and cost; L e The environmental impact loss function reflects resource consumption and pollution; λ1, λ2, and λ3 are weighting coefficients that are dynamically adjusted by the enterprise according to its strategic objectives.

[0018] By adopting the above technical solutions and using distributed storage (such as Hadoop / HDFS architecture), nodes can be added as needed, supporting PB-level cardboard box full lifecycle data storage, solving the storage bottleneck caused by the explosion of data volume in traditional single-machine storage, and using the layered architecture of distributed storage (hot data is stored on SSD, and cold data is archived to mechanical hard disk), the storage cost of massive historical data (such as cardboard box recycling records of more than 3 years) is reduced. By using deep learning models (such as LSTM and CNN) to process multi-source data from production, logistics, and recycling (with an average daily data processing volume of ≥5 million records), hidden patterns that traditional statistical methods cannot identify are captured. Based on real-time order data, the system predicts the production capacity gap for the next 7 days and automatically adjusts the shift schedule to improve equipment utilization.

[0019] On the other hand, an intelligent carton production management method is applied to an intelligent carton production management system, and the management method includes the following steps: S1. After receiving an order, the production management module arranges the production plan according to the order. The order management unit builds an order priority evaluation model and uses the order priority evaluation model to determine the order processing order by comprehensively considering the urgency of the order, the batch size, and the customer weight. The production scheduling model established by the production scheduling unit formulates a production plan to minimize the production cycle by taking into account equipment capacity and material constraints. S2. The tracking module is used to identify and monitor the carton in real time via Internet devices, collect the carton's location and status information, and transmit the processed data to the data analysis module; S3. The recycling module receives recycling requests and arranges recycling tasks. It uses a recycling demand prediction model to predict the recycling demand in each area. Then, through a recycling path optimization model based on an improved genetic algorithm, it generates recycling tasks by comprehensively considering recycling costs, time windows, and cardboard box integrity rates, and schedules recycling personnel to recycle the cardboard boxes. S4. The data analysis module is used to store and analyze data throughout the entire lifecycle of cardboard boxes, and to optimize production plans and recycling strategies.

[0020] By adopting the above technical solutions, the cardboard box production process can be planned in advance, the production efficiency of cardboard boxes can be optimized, the cardboard boxes can be accurately tracked and scheduled, the cardboard box recycling rate can be improved, and the cardboard boxes can be reused multiple times.

[0021] The technical effects and advantages of this application are as follows: Compared with existing technologies, this intelligent cardboard box production management system and method realizes intelligent management of the entire process of cardboard box production, use and recycling, and improves management efficiency through the optimization of models and formulas of each module; This intelligent cardboard box production management system and method realizes intelligent management of the entire process of cardboard box production, use and recycling. Through the optimization of models and formulas of each module, management efficiency is improved. This intelligent cardboard box production management system and method utilizes the prediction and scheduling model of the recycling module to improve the recycling rate and resource utilization of cardboard boxes, while reducing production costs and environmental pollution. Attached Figure Description

[0022] Figure 1 This is a schematic diagram of the system flow of this application; Figure 2 This is a schematic diagram of the method flow of this application.

[0023] The attached diagram is labeled as follows: 1. Production Management Module; 101. Order Management Unit; 102. Production Scheduling Unit; 2. Tracking Module; 201. Identification Unit; 202. Monitoring Unit; 3. Recycling Module; 301. Recycling Request Unit; 302. Recycling Scheduling Unit; 4. Data Analysis Module; 401. Data Storage Unit; 402. Analysis Unit. Detailed Implementation

[0024] The technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, and not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0025] Example 1 As attached Figure 1 The intelligent cardboard box production management system shown includes a production management module 1, a tracking module 2, a recycling module 3, and a data analysis module 4. Production management module 1 is used to arrange production plans according to orders after receiving them, and the output of production management module 1 is electrically connected to the input of tracking module 2; In a preferred embodiment, the production management module 1 includes an order management unit 101 and a production scheduling unit 102. The order management unit 101 is used to construct an order priority evaluation model. After receiving an order, it uses the order priority evaluation model to comprehensively consider the order's urgency, batch size, and customer weight to determine the order processing order. The order priority calculation formula in the order priority evaluation model is: Among them, P i Let D be the priority of order i. i For the delivery date of order i, T c Q is the current time. i Let Q be the quantity of order i. max C is the maximum number of orders set by the system. i The customer weighting coefficient is determined by the enterprise based on the customer's historical purchase amount, cooperation period and credit rating. w1, w2 and w3 are weighting factors, and w1+w2+w3=1.

[0026] The order priority assessment model aims to scientifically and rationally determine the order processing sequence by comprehensively considering key factors such as order urgency, batch size, and customer weight. This effectively improves enterprise operational efficiency and customer satisfaction. Order urgency directly relates to customer expectations of delivery time and is one of the key factors in determining order priority. Batch size affects the enterprise's production scale efficiency; larger orders may have an advantage in resource allocation. Customer weight reflects the customer's value contribution to the enterprise; orders from important customers often need to be prioritized. By comprehensively considering these three factors, the model can balance enterprise production and customer demand, achieving optimal resource allocation.

[0027] In a preferred embodiment, the production scheduling unit 102 is used to establish a production scheduling model based on constraint theory, with the goal of minimizing the production cycle. It formulates a production plan based on equipment capacity and material constraints. Specifically, the production scheduling model is: minT = max{B j}, j=1,2,...,m, the process sequence constraint is: B i ≥B k +t ik Equipment capacity constraints are: Material requirement constraint is: S i ≥R i ; Where T is the total production cycle, B j Let m be the completion time of equipment j, m be the number of equipment, and B be the completion time of equipment j. i B k The completion times of processes i and k are respectively, t ik x is the preparation time from process i to process k. ij B is the time for equipment j to process process i. apj S represents the available capacity of equipment j. i R is the material supply quantity for process i. i Let n be the material requirement for process i, and n be the number of processes.

[0028] The tracking module 2 is used to identify and monitor the location and status information of the cardboard boxes in real time through Internet devices, and the output of the tracking module 2 is electrically connected to the input of the recycling module 3. In a preferred embodiment, the tracking module 2 includes an identification unit 201 and a monitoring unit 202. The identification unit 201 uses an RFID tag or an NFC tag to assign a unique electronic identification code to each carton. The monitoring unit 202 is used to build a real-time status monitoring model based on the Internet of Things. It calculates the turnover efficiency and abnormal probability of the carton through the data collected by the device and uploads the obtained data to the data analysis module 4. In the real-time status monitoring model, the electronic identification code on the cardboard box is read by an IoT device, and then the read electronic identification code information data is transmitted to the monitoring unit 202. The formula for calculating the circulation efficiency in the real-time status monitoring model is: Where E is the carton turnover efficiency, L is the actual turnover distance of the carton, and T is the total turnover distance. f The preset standard turnaround time is η, which is the environmental interference coefficient and its value ranges from [0.8 to 1.2].

[0029] The formula for calculating the anomaly probability in the real-time status monitoring model is: Among them, P a Let X be the probability of an abnormal state of the cardboard box, X be a vector of multiple state parameters including position offset, vibration frequency, temperature and humidity, and α and β be model parameters, which are determined by training with historical data.

[0030] The recycling module 3 is used to receive recycling requests and arrange recycling tasks, and the output of the recycling module 3 is electrically connected to the input of the data analysis module 4. In a preferred embodiment, the recycling module 3 includes a recycling request unit 301 and a recycling scheduling unit 302. The recycling request unit 301 is used to design a recycling demand prediction model, combining historical recycling data, peak season patterns in logistics, and regional economic indicators to predict the recycling demand in each region. The recycling demand prediction model is specifically as follows: Among them, F r Let X be the regional recycling demand, a0 be a constant term, and X be the recycling demand. i For characteristics related to historical recovery volume, Y j For logistics cycle characteristics, Z m As a characteristic of regional economy, a i b j c m Here, ε is the regression coefficient, and ε is the random error term. φ and ψ represent the corresponding number of features.

[0031] The recycling scheduling unit 302 is used to construct a recycling path optimization model based on an improved genetic algorithm. This model comprehensively considers recycling cost, time window, and cardboard box integrity rate to schedule cardboard box recycling. The recycling path optimization model includes a recycling path optimization objective function: The constraints are: x ij ∈{0,1}; where C is the total recovery cost, d ij x is the distance from recycling point i to recycling point j; ij For decision variables, 1 indicates from i to j, 0 otherwise; h i Let t be the time penalty coefficient for recycling point i. i e represents the actual arrival time.i p is the deadline for the time window; i w′ is the value coefficient of the cardboard boxes at recycling point i. i n represents the cardboard box integrity rate; n′ represents the number of recycling points.

[0032] It has achieved intelligent management of the entire process of cardboard box production, use and recycling, and improved management efficiency through the optimization of models and formulas in each module.

[0033] Data analytics module 4 is used to store and analyze data throughout the entire lifecycle of cardboard boxes, and to optimize production planning and recycling strategies.

[0034] In a preferred embodiment, the data analysis module 4 includes a data storage unit 401 and an analysis unit 402. The data storage unit 401 adopts a distributed storage structure to store the entire lifecycle data of the cardboard box. The analysis unit 402 is used to construct a deep learning-based lifecycle optimization model. The lifecycle optimization model is trained with multi-dimensional data to optimize production plans and recycling strategies. Specifically, the lifecycle optimization model is: minJ = λ1L p +λ2L r +λ3L e Where J is the comprehensive optimization objective function; L p The loss function in the production process reflects production efficiency and cost; L r The loss function for the recycling process reflects the recycling efficiency and cost; L e The environmental impact loss function reflects resource consumption and pollution; λ1, λ2, and λ3 are weighting coefficients that enterprises dynamically adjust according to their strategic goals. Distributed storage (such as Hadoop / HDFS architecture) is adopted, and nodes can be added as needed. It supports PB-level cardboard box full lifecycle data storage, solving the storage bottleneck caused by the explosion of data volume in traditional single-machine storage. By utilizing the layered architecture of distributed storage (hot data is stored on SSDs, and cold data is archived to mechanical hard drives), the storage cost of massive historical data (such as cardboard box recycling records of more than 3 years) is reduced.

[0035] Example 2 The intelligent cardboard box production management method includes the following steps: S1. After receiving an order, the production management module 1 arranges the production plan according to the order. The order management unit 101 constructs an order priority evaluation model. The order priority evaluation model is used to determine the order processing order by comprehensively considering the urgency of the order, the batch size, and the customer weight. The production scheduling model established by the production scheduling unit 102 formulates the production plan to minimize the production cycle by considering equipment capacity and material constraints. S2. Tracking module 2 is used to identify and monitor the carton in real time through Internet devices, collect the location and status information of the carton, and transmit the processed data to data analysis module 4; S3. Recycling module 3 receives recycling requests and arranges recycling tasks. It uses a recycling demand prediction model to predict the recycling demand in each area. Then, through a recycling path optimization model based on an improved genetic algorithm, it generates recycling tasks by comprehensively considering recycling costs, time windows, and cardboard box integrity rates, and schedules recycling personnel to recycle the cardboard boxes. S4. Data Analysis Module 4 is used to store and analyze data throughout the entire lifecycle of cardboard boxes, and to optimize production planning and recycling strategies.

[0036] It can efficiently manage cardboard box production, achieve precise tracking and scheduling of cardboard boxes, improve cardboard box recycling rate, and enable cardboard boxes to be reused multiple times.

[0037] Finally: The above description is only a preferred embodiment of this application and is not intended to limit this application. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of this application should be included within the protection scope of this application.

Claims

1. An intelligent cardboard box production management system, comprising a production management module (1), a tracking module (2), a recycling module (3), and a data analysis module (4), characterized in that: The production management module (1) is used to arrange the production plan according to the order after receiving the order, and the output end of the production management module (1) is electrically connected to the input end of the tracking module (2); The tracking module (2) is used to identify the cardboard box and collect the location and status information of the cardboard box in real time through Internet devices, and the output end of the tracking module (2) is electrically connected to the input end of the recycling module (3); The recycling module (3) is used to receive recycling requests and arrange recycling tasks, and the output end of the recycling module (3) is electrically connected to the input end of the data analysis module (4); The data analysis module (4) is used to store and analyze the full life cycle data of the carton and optimize production plans and recycling strategies.

2. The intelligent cardboard box production management system according to claim 1, characterized in that: The production management module (1) includes an order management unit (101) and a production scheduling unit (102). The order management unit (101) is used to construct an order priority evaluation model. After receiving an order, the order priority evaluation model is used to determine the order processing order by comprehensively considering the urgency of the order, the batch size, and the customer weight. The order priority calculation formula in the order priority evaluation model is as follows: Among them, P i Let D be the priority of order i. i For the delivery date of order i, T c Q is the current time. i Let Q be the quantity of order i. max C is the maximum number of orders set by the system. i The customer weighting coefficient is determined by the enterprise based on the customer's historical purchase amount, cooperation period and credit rating. w1, w2 and w3 are weighting factors, and w1+w2+w3=1.

3. The intelligent cardboard box production management system according to claim 2, characterized in that: The production scheduling unit (102) is used to establish a production scheduling model based on constraint theory, with the goal of minimizing the production cycle. It formulates a production plan based on equipment capacity and material constraints. Specifically, the production scheduling model is: minT = max{B j }, j=1,2,...,m, the process sequence constraint is: B i ≥B k +t ik Equipment capacity constraints are: Material requirement constraint is: S i ≥R i ; Where T is the total production cycle, B j Let m be the completion time of equipment j, m be the number of equipment, and B be the completion time of equipment j. i B k The completion times of processes i and k are respectively, t ik x is the preparation time from process i to process k. ij B is the time for equipment j to process process i. apj S represents the available capacity of equipment j. i R is the material supply quantity for process i. i Let n be the material requirement for process i, and n be the number of processes.

4. The intelligent cardboard box production management system according to claim 1, characterized in that: The tracking module (2) includes an identification unit (201) and a monitoring unit (202). The identification unit (201) assigns a unique electronic identification code to each carton using RFID or NFC tags. The monitoring unit (202) is used to construct a real-time status monitoring model based on the Internet of Things (IoT). It calculates the turnover efficiency and abnormal probability of the cartons using data collected by the device and uploads the obtained data to the data analysis module (4). In the real-time status monitoring model, the electronic identification code on the carton is read by the IoT device, and then the read electronic identification code information data is transmitted to the monitoring unit (202). The turnover efficiency calculation formula in the real-time status monitoring model is: Where E is the carton turnover efficiency, L is the actual turnover distance of the carton, and T is the total turnover distance. f The preset standard turnaround time is η, which is the environmental interference coefficient and its value ranges from [0.8 to 1.2].

5. The intelligent cardboard box production management system according to claim 4, characterized in that: The formula for calculating the anomaly probability in the real-time status monitoring model is as follows: Among them, P a Let X be the probability of an abnormal state of the cardboard box, X be a vector of multiple state parameters including position offset, vibration frequency, temperature and humidity, and α and β be model parameters, which are determined by training with historical data.

6. The intelligent cardboard box production management system according to claim 5, characterized in that: The recycling module (3) includes a recycling request unit (301) and a recycling scheduling unit (302). The recycling request unit (301) is used to design a recycling demand prediction model, combining historical recycling data, logistics peak season patterns, and regional economic indicators to predict the recycling demand in each region. The recycling demand prediction model is specifically as follows: Among them, F r Let X be the regional recycling demand, a0 be a constant term, and X be the recycling demand. i For characteristics related to historical recovery volume, Y j For logistics cycle characteristics, Z m As a characteristic of regional economy, a i b j c m Here, ε is the regression coefficient, and ε is the random error term. φ and ψ represent the corresponding number of features.

7. The intelligent cardboard box production management system according to claim 1, characterized in that: The recycling scheduling unit (302) is used to construct a recycling path optimization model based on an improved genetic algorithm, which comprehensively considers recycling cost, time window, and cardboard box integrity rate to schedule the recycling of cardboard boxes. The recycling path optimization model is set with the following objective function: The constraints are: Where C is the total recovery cost, d ij x is the distance from recycling point i to recycling point j; ij For decision variables, 1 indicates from i to j, 0 otherwise; h i Let t be the time penalty coefficient for recycling point i. i e represents the actual arrival time. i p is the deadline for the time window; i w′ is the value coefficient of the cardboard boxes at recycling point i. i n represents the cardboard box integrity rate; n′ represents the number of recycling points.

8. The intelligent cardboard box production management system according to claim 1, characterized in that: The data analysis module (4) includes a data storage unit (401) and an analysis unit (402). The data storage unit (401) adopts a distributed storage structure to store the full life cycle data of the cardboard box. The analysis unit (402) is used to construct a full life cycle optimization model based on deep learning. The full life cycle optimization model is trained with multi-dimensional data to optimize the production plan and recycling strategy. The full life cycle optimization model is specifically: minJ=λ1L p +λ2L r +λ3L e Where J is the comprehensive optimization objective function; L p The loss function in the production process reflects production efficiency and cost; L r The loss function for the recycling process reflects the recycling efficiency and cost; L e The environmental impact loss function reflects resource consumption and pollution; λ1, λ2, and λ3 are weighting coefficients that are dynamically adjusted by the enterprise according to its strategic objectives.

9. A smart cardboard box production management method, characterized in that, The intelligent carton production management system, applied to any one of claims 1-8, comprises the following steps: S1. Production Management Module (1) After receiving an order, it arranges the production plan according to the order. It constructs an order priority evaluation model through the order management unit (101), and uses the order priority evaluation model to comprehensively consider the urgency of the order, the batch size and the customer weight to determine the order processing order. Through the production scheduling model established by the production scheduling unit (102), it formulates a production plan based on equipment capacity and material constraints to obtain the minimum production cycle. S2. The tracking module (2) is used to identify and monitor the carton in real time through Internet devices, collect the location and status information of the carton, and transmit the processed data to the data analysis module (4); S3. Recycling module (3) receives recycling requests and arranges recycling tasks. It uses a recycling demand prediction model to predict the recycling demand in each area. Then, it uses a recycling path optimization model based on an improved genetic algorithm to generate recycling tasks by comprehensively considering recycling costs, time windows, and cardboard box integrity rates, and schedules recycling personnel to recycle the cardboard boxes. S4. Data Analysis Module (4) is used to store and analyze data throughout the entire lifecycle of cartons and to optimize production plans and recycling strategies.

Images