Cargo loading and unloading logistics information management system and method based on big data

Abstract

The invention discloses a cargo loading and unloading logistics information management system and method based on big data, and relates to the technical field of logistics management, and the system comprises an intelligent cargo tracking module, an intelligent prediction module, a loading and unloading path optimization module, an intelligent safety monitoring module, a dynamic inventory management module, and a supply chain cooperation module. And operation is carried out based on the cargo loading and unloading logistics information management system. According to the cargo loading and unloading logistics information management system and method based on big data, data can be analyzed and processed in real time, so that the safety and efficiency of overall logistics operation are improved, the transportation cost is reduced, intelligent management is realized, the transportation time and cost are reduced through accurate demand prediction and dynamic path optimization, and meanwhile, the transportation efficiency is improved. The real-time safety monitoring can reduce the probability of accidents and protect the safety of employees and assets.

Description

Technical Field

[0001] The present invention relates to the technical field of logistics management, and in particular to a cargo loading and unloading logistics information management system and method based on big data. Background Art

[0002] With the acceleration of globalization and the rapid development of e-commerce, the logistics industry is facing growing demands, especially in the field of cargo handling, where efficiency and safety have become the key to corporate competition. However, existing technical means often rely on traditional data processing methods, which make it difficult to effectively integrate information from different sources, such as video surveillance, sensor data, real-time traffic information, and biometric data. This leads to waste of resources, inefficient scheduling, and potential safety hazards. In addition, traditional demand forecasting methods are usually based on historical data, ignoring the impact of external factors (such as weather changes, traffic conditions, etc.), which greatly reduces the accuracy of forecast results. At the same time, in terms of safety management, the lack of real-time dynamic monitoring capabilities makes the early warning response to unsafe operations delayed, increasing the risk of accidents.

[0003] In order to solve the above problems, the cargo loading and unloading logistics information management system based on big data came into being. Summary of the invention

[0004] In view of the deficiencies in the prior art, the present invention provides a cargo loading and unloading logistics information management system and method based on big data to solve the problems raised in the above background technology.

[0005] To achieve the above-mentioned purpose, the present invention provides the following technical solutions: a cargo loading and unloading logistics information management system based on big data, comprising an intelligent cargo tracking module, an intelligent prediction module, an optimized loading and unloading path module, an intelligent safety monitoring module, a dynamic inventory management module and a supply chain collaboration module;

[0006] The intelligent cargo tracking module uses the Internet of Things technology and RFID tags to monitor and track each piece of cargo during the loading and unloading process in real time, and the location information and status of the cargo can be viewed in real time through a mobile phone or computer;

[0007] The intelligent prediction module uses big data data mining technology to analyze historical loading and unloading data based on machine learning, and generates accurate demand forecasts by comprehensively analyzing factors such as weather, traffic conditions and holidays;

[0008] The loading and unloading path optimization module optimizes the loading and unloading path using an algorithm and dynamically adjusts the optimal path based on real-time updated traffic data and equipment status;

[0009] The intelligent safety monitoring module monitors the potential safety hazards in the loading and unloading process in real time based on video monitoring and sensor networks, and uses deep learning algorithms to automatically identify abnormal behaviors and issue alarms in a timely manner;

[0010] The dynamic inventory management module monitors and adjusts inventory status through real-time data analysis;

[0011] The supply chain collaboration module integrates data from all parties to collaborate with upstream and downstream parties in the supply chain, and automates cargo loading and unloading contract execution and fee payment by sharing data and using smart contracts.

[0012] To further optimize the technical solution, the intelligent cargo tracking module uses blockchain technology to store all the transfer information of the cargo during the loading and unloading process, ensuring that the data during the cargo loading and unloading process cannot be tampered with.

[0013] To further optimize the technical solution, the intelligent prediction module uses a combination of time series analysis and regression model to predict future cargo handling demand and transportation time;

[0014] By using the ARIMA model or SARIMA model, the intelligent forecasting module captures the seasonal fluctuations and long-term trends of historical demand, identifies cyclical changes by analyzing the autocorrelation of cargo handling data, and predicts future demand. A multivariate regression model is established, with historical demand as the dependent variable and weather, traffic conditions, and holidays as independent variables, to output forecasts of future cargo handling demand and transportation time.

[0015] To further optimize this technical solution, the multivariate regression model is shown in the following formula:

[0016] Y=β0+β1X1+β2X2+...+β n X n +∈;

[0017] in,

[0018] Y is the dependent variable, i.e. the target variable, such as cargo handling demand or transportation time;

[0019] X1,X2,...,X n are independent variables, i.e. characteristic variables, such as weather, traffic conditions, and holiday factors;

[0020] β0 is the intercept, i.e. the constant term, which represents the value of the dependent variable when the independent variable is zero;

[0021] β1, β2, ..., β n is the regression coefficient, which indicates the influence of the independent variable on the dependent variable;

[0022] ε is the error term.

[0023] To further optimize the technical solution, the multivariate regression model includes the following process when predicting future cargo handling demand and transportation time:

[0024] Data preparation: Collect and organize historical loading and unloading data, including cargo loading and unloading demand, transportation time, and related independent variables such as weather, traffic conditions, and holiday factors;

[0025] Model training: The historical loading and unloading data are divided into a training set and a test set. The training set is used to fit the multivariate regression model, and the regression coefficients β1, β2, ..., β n ;

[0026] Model validation: Use the test set to evaluate the performance of the multivariate regression model and calculate the prediction error to verify the accuracy of the multivariate regression model. If the model performs well, it is directly used for prediction.

[0027] Future prediction: Collect future independent variable data, such as expected weather, traffic conditions, and holiday factors. The data is obtained through weather forecasts and traffic flow forecasts. Substitute the independent variables into the trained multivariate regression model and calculate the predicted value Y, then:

[0028] Y 预测 =β0+β1X 1,未来 +β2X 2,未来 +…+β n X n，未来 ;

[0029] Output: Generate forecasts of future cargo handling demand and transportation time to help logistics companies allocate resources and adjust cargo handling plans.

[0030] To further optimize the technical solution, the loading and unloading path optimization module performs path optimization based on an ant colony algorithm, and the algorithm includes the following construction steps:

[0031] First, the path is constructed. Each ant randomly selects a path. The path selection probability is determined by pheromone and heuristic information:

[0032]

[0033] Among them, τ ij is the pheromone intensity, η ij is heuristic information, such as the inverse of the distance, and α and β are weight parameters;

[0034] Secondly, pheromone is updated according to the path quality of the ants:

[0035] τ ij =(1-ρ)τij +△τ ij ;

[0036] Where ρ is the volatility, Δτ ij is the contribution of the path, a function of path quality and length;

[0037] Finally, iterations are performed to repeat path construction and pheromone updating until a termination condition is reached, such as reaching the optimal solution or the number of iterations.

[0038] To further optimize the technical solution, the loading and unloading path optimization module optimizes the cargo loading and unloading path based on the ant colony algorithm, including the following processes:

[0039] Determine loading and unloading points: List all loading and unloading points that need to be visited, such as warehouses, ports, and distribution centers, and clearly define optimization goals, such as minimizing transportation time and cost or maximizing loading efficiency;

[0040] Initialize parameters: set the number of ants, set pheromones and heuristic factors, and define the parameters;

[0041] Cargo loading and unloading path construction: Each ant starts from the starting point, selects the next loading and unloading point based on the selection probability, combined with pheromone and heuristic information, and updates the visited path until all loading and unloading points are visited and return to the starting point;

[0042] Pheromone update: Calculate the quality of the path taken by each ant, such as transportation time and cost, and update the pheromone according to the path quality, Δτ ij Proportional to the quality of the path;

[0043] Iteration: Perform multiple iterations, allowing ants to continuously explore new paths and update pheromones, and monitor the best path and corresponding quality of each iteration;

[0044] Set termination conditions: reaching the maximum number of iterations, the path quality change is less than the set threshold in multiple iterations, and a path that meets the optimization goal is found;

[0045] Result output: record the best path found during the iteration process and its corresponding transportation time and cost, and visualize the path;

[0046] Dynamic adjustment: Regularly update traffic data and weather conditions, dynamically adjust pheromones, and re-run the ant colony algorithm based on new data to ensure that the path optimization matches the real-time situation.

[0047] To further optimize the technical solution, the abnormal behavior scoring model is constructed in the intelligent security monitoring module, including the following processes:

[0048] Input data, data includes video stream data V t: Video frame at time t; sensor data S t : Real-time sensor parameters including temperature, humidity, and location; biometric data B t : Employees’ biometric data, such as facial recognition, fingerprints;

[0049] Output result, output abnormal behavior score A t : reflects whether the operation at the current time t is normal;

[0050] Design an abnormal behavior scoring model and integrate multiple features. The model is as follows:

[0051] A t =f(V t , S t , B t )=w1·F V (V t )+w2·F S (S t )+w3·F B (B t );

[0052] in,

[0053] F V (V t ) is a deep learning feature extraction function based on video stream data, which uses a convolutional neural network (CNN) to extract behavioral features in key frames, expressed as:

[0054] F V (V t )=CNN(V t );

[0055] F S (S t ) is the feature extraction based on sensor data, and the state change features are extracted using the time series analysis method, which is expressed as:

[0056] F S (S t )=TS(S t );

[0057] F B (B t ) is a feature extraction based on biometric data, using a classification algorithm such as a support vector machine or a random forest to determine the compliance of the operation, expressed as:

[0058] F B (B t )=Classifier(B t );

[0059] w1, w2, and w3 are weight coefficients, reflecting the importance of different features in abnormal behavior scoring;

[0060] Determine abnormal behavior. When the score is A t When a certain threshold value T is exceeded, an alarm is issued.

[0061] To further optimize the technical solution, the dynamic inventory management module also automatically adjusts inventory levels according to the inflow and outflow of goods, demand forecasts and market changes, thereby reducing inventory costs and improving turnover rates;

[0062] It also has a built-in intelligent replenishment algorithm that combines big data analysis to predict the best time to replenish and prevent out-of-stock or overstocking.

[0063] A cargo handling logistics information management method based on big data is operated based on the above cargo handling logistics information management system based on big data, and includes the following specific steps:

[0064] S1. Data collection;

[0065] Collect historical loading and unloading data, real-time traffic data, weather information, sensor data, and biometric data to build a data warehouse;

[0066] S2, data preprocessing;

[0067] Clean, deduplicate and format the collected data to ensure data integrity and consistency;

[0068] S3. Demand forecasting;

[0069] Use the intelligent forecasting module to apply time series analysis and regression models to predict future cargo handling needs and transportation times;

[0070] S4, path optimization;

[0071] Apply ant colony algorithm to optimize loading and unloading routes to minimize transportation time and cost, while dynamically updating routes to cope with emergencies;

[0072] S5. Security monitoring;

[0073] Implementing an intelligent safety monitoring module that monitors loading and unloading operations in real time through video surveillance and sensor technology, and uses deep learning algorithms to identify abnormal behavior;

[0074] S6. Dynamic inventory management;

[0075] Dynamically adjust inventory levels and optimize resource allocation based on real-time data and demand forecasts;

[0076] S7, supply chain collaboration;

[0077] Through the supply chain collaboration module, upstream and downstream data are integrated to promote information sharing and decision-making collaboration, thereby improving overall operational efficiency.

[0078] Compared with the prior art, the present invention provides a cargo loading and unloading logistics information management system and method based on big data, which has the following beneficial effects:

[0079] This cargo loading and unloading logistics information management system and method based on big data can analyze and process data in real time, thereby improving the safety and efficiency of overall logistics operations, reducing transportation costs, and realizing intelligent management. Through accurate demand forecasting and dynamic path optimization, it can reduce transportation time and costs. At the same time, real-time safety monitoring will reduce the probability of accidents and protect the safety of employees and assets. BRIEF DESCRIPTION OF THE DRAWINGS

[0080] Figure 1 This is a structural schematic diagram of a cargo loading and unloading logistics information management system based on big data proposed by the present invention;

[0081] Figure 2 This is a flow chart of a multivariate regression model in a cargo handling logistics information management system based on big data proposed by the present invention;

[0082] Figure 3 This is a schematic diagram of a process for optimizing loading and unloading paths in a cargo loading and unloading logistics information management system based on big data proposed by the present invention;

[0083] Figure 4 This is a flow chart of a cargo loading and unloading logistics information management method based on big data proposed by the present invention. DETAILED DESCRIPTION

[0084] The following will be combined with the embodiments of the present invention to clearly and completely describe the technical solutions 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.

[0085] Embodiment 1:

[0086] See also Figure 1 , a cargo loading and unloading logistics information management system based on big data, including intelligent cargo tracking module, intelligent prediction module, optimized loading and unloading path module, intelligent safety monitoring module, dynamic inventory management module and supply chain collaboration module.

[0087] The intelligent cargo tracking module uses the Internet of Things technology and RFID tags to monitor and track each piece of cargo in the loading and unloading process in real time, and the location information and status of the cargo can be viewed in real time through a mobile phone or computer.

[0088] In this embodiment, the intelligent cargo tracking module uses blockchain technology to store all the transfer information of the cargo during the loading and unloading process, ensuring that the data during the cargo loading and unloading process cannot be tampered with.

[0089] The intelligent prediction module uses big data data mining technology to analyze historical loading and unloading data based on machine learning, and generates accurate demand forecasts by conducting a comprehensive analysis of weather, traffic conditions and holidays.

[0090] In this embodiment, the intelligent prediction module uses a combination of time series analysis and regression model to predict future cargo handling demand and transportation time, and identifies periodic changes by analyzing the autocorrelation of data, thereby predicting future demand.

[0091] By using the ARI MA model or SARI MA model, the intelligent forecasting module captures the seasonal fluctuations and long-term trends of historical demand, identifies cyclical changes by analyzing the autocorrelation of cargo loading and unloading data, predicts future demand, and establishes a multivariate regression model, taking historical demand as the dependent variable and weather, traffic conditions and holiday factors as independent variables, and outputs forecasts of future cargo loading and unloading demand and transportation time.

[0092] Furthermore, the multiple regression model is shown in the following formula:

[0093] Y=β0+β1X1+β2X2+...+β n X n +∈;

[0094] in,

[0095] Y is the dependent variable, i.e. the target variable, such as cargo handling demand or transportation time;

[0096] X1,X2,...,X n are independent variables, i.e. characteristic variables, such as weather, traffic conditions, and holiday factors;

[0097] β0 is the intercept, i.e. the constant term, which represents the value of the dependent variable when the independent variable is zero;

[0098] β1, β2, ..., β n is the regression coefficient, which indicates the influence of the independent variable on the dependent variable;

[0099] ∈ is the error term.

[0100] like Figure 2 As shown, further, the multivariate regression model includes the following processes when predicting future cargo handling demand and transportation time:

[0101] Data preparation: Collect and organize historical loading and unloading data, including cargo loading and unloading demand, transportation time, and related independent variables such as weather, traffic conditions, and holiday factors;

[0102] Model training: The historical loading and unloading data are divided into a training set and a test set. The training set is used to fit the multivariate regression model, and the regression coefficients β1, β2, ..., β n ;

[0103] Model validation: Use the test set to evaluate the performance of the multivariate regression model and calculate the prediction error to verify the accuracy of the multivariate regression model. If the model performs well, it is directly used for prediction.

[0104] Future prediction: Collect future independent variable data, such as expected weather, traffic conditions, and holiday factors. The data is obtained through weather forecasts and traffic flow forecasts. Substitute the independent variables into the trained multivariate regression model and calculate the predicted value Y, then:

[0105] Y 预测 =β0+β1X 1,未来 +β2X 2,未来 +…+β n X n，未来 ;

[0106] Output: Generate forecasts of future cargo handling demand and transportation time to help logistics companies allocate resources and adjust cargo handling plans.

[0107] In this embodiment, it is assumed that a model is established to predict the cargo demand Y, where the independent variables include weather temperature X1, traffic flow X2, and holiday sign X3:

[0108] Y=50+1.2X1-0.5X2+10X3

[0109] If the future temperature is 30 degrees, the traffic volume is 200, and it is assumed to be a holiday X3 = 1, then the predicted demand is:

[0110] Y 预测 =50+1.2×30-0.5×200+10×1=50+36-100+10=-4In actual applications, if the prediction result is negative, the model may need to be adjusted to ensure that all independent variables have a reasonable impact on the target.

[0111] The loading and unloading path optimization module optimizes the loading and unloading path using an algorithm, and dynamically adjusts the optimal path through real-time updated traffic data and equipment status.

[0112] In this embodiment, the loading and unloading path optimization module performs path optimization based on an ant colony algorithm, and the algorithm includes the following construction steps:

[0113] First, the path is constructed. Each ant randomly selects a path. The path selection probability is determined by pheromone and heuristic information:

[0114]

[0115] Among them, τ ij is the pheromone intensity, η ij is heuristic information, such as the inverse of the distance, and α and β are weight parameters;

[0116] Secondly, pheromone is updated according to the path quality of the ants:

[0117] τ ij =(1-ρ)τ ij +Δτ ij ;

[0118] Where ρ is the volatility, Δτ ij is the contribution of the path, a function of path quality and length;

[0119] Finally, iterations are performed to repeat path construction and pheromone updating until a termination condition is reached, such as reaching the optimal solution or the number of iterations.

[0120] With real-time updated traffic data and equipment status, the system can:

[0121] Rerun the model at regular intervals to re-evaluate the path using new data.

[0122] Dynamically adjust pheromone concentration or path selection probability based on real-time data to ensure rapid response to emergencies.

[0123] like Figure 3 As shown, further, the loading and unloading path optimization module optimizes the cargo loading and unloading path based on the ant colony algorithm, including the following process:

[0124] Determine loading and unloading points: List all loading and unloading points that need to be visited, such as warehouses, ports, and distribution centers, and clearly define optimization goals, such as minimizing transportation time and cost or maximizing loading efficiency;

[0125] Initialize parameters: set the number of ants, set pheromones and heuristic factors, and define the parameters;

[0126] Cargo loading and unloading path construction: Each ant starts from the starting point, selects the next loading and unloading point based on the selection probability, combined with pheromone and heuristic information, and updates the visited path until all loading and unloading points are visited and return to the starting point;

[0127] Pheromone update: Calculate the quality of the path taken by each ant, such as transportation time and cost, and update the pheromone according to the path quality, Δτ ij Proportional to the quality of the path;

[0128] Iteration: Perform multiple iterations, allowing ants to continuously explore new paths and update pheromones, and monitor the best path and corresponding quality of each iteration;

[0129] Set termination conditions: reaching the maximum number of iterations, the path quality change is less than the set threshold in multiple iterations, and a path that meets the optimization goal is found;

[0130] Result output: record the best path found during the iteration process and its corresponding transportation time and cost, and visualize the path;

[0131] Dynamic adjustment: Regularly update traffic data and weather conditions, dynamically adjust pheromones, and re-run the ant colony algorithm based on new data to ensure that the path optimization matches the real-time situation.

[0132] The intelligent safety monitoring module monitors the potential safety hazards in the loading and unloading process in real time based on video monitoring and sensor networks, and uses deep learning algorithms to automatically identify abnormal behaviors and issue alarms in a timely manner.

[0133] In this embodiment, the abnormal behavior scoring model is constructed in the intelligent security monitoring module, including the following processes:

[0134] Input data, data includes video stream data V t : Video frame at time t; sensor data S t : Real-time sensor parameters including temperature, humidity, and location; biometric data B t : Employees’ biometric data, such as facial recognition, fingerprints;

[0135] Output result, output abnormal behavior score A t : reflects whether the operation at the current time t is normal;

[0136] Design an abnormal behavior scoring model and integrate multiple features. The model is as follows:

[0137] A t =f(V t , S t , B t )=w1·F V (Vt )+w2F S (S t )+w3·F B (B t );

[0138] in,

[0139] F V (V t ) is a deep learning feature extraction function based on video stream data, which uses a convolutional neural network (CNN) to extract behavioral features in key frames, expressed as:

[0140] F V (V t )=CNN(V t );

[0141] F S (S t ) is the feature extraction based on sensor data, and the state change features are extracted using the time series analysis method, which is expressed as:

[0142] F S (S t )=TS(S t );

[0143] F B (B t ) is a feature extraction based on biometric data, using a classification algorithm such as a support vector machine or a random forest to determine the compliance of the operation, expressed as:

[0144] F B (B t )=Classifier(B t );

[0145] w1, w2, and w3 are weight coefficients, reflecting the importance of different features in abnormal behavior scoring;

[0146] Determine abnormal behavior. When the score is A t When a certain threshold value T is exceeded, an alarm is issued.

[0147] The model combines video surveillance, sensor data, and biometric data to comprehensively assess operational safety. The weight coefficients w1, w2, and w3 can be dynamically adjusted based on historical data and real-time feedback to adapt to different environments and scenarios. By continuously learning new behavior patterns, the model can optimize feature extraction methods and improve the accuracy of abnormal behavior identification.

[0148] The dynamic inventory management module monitors and adjusts the inventory status through real-time data analysis.

[0149] In this embodiment, the dynamic inventory management module also automatically adjusts inventory levels based on the inflow and outflow of goods, demand forecasts, and market changes, thereby reducing inventory costs and improving turnover rates;

[0150] It also has a built-in intelligent replenishment algorithm that combines big data analysis to predict the best time to replenish and prevent out-of-stock or overstocking.

[0151] The supply chain collaboration module integrates data from all parties to collaborate with upstream and downstream parties in the supply chain, and automates cargo loading and unloading contract execution and fee payment by sharing data and using smart contracts.

[0152] In this embodiment, by sharing data, enterprises can adjust production and transportation plans in real time to ensure the smoothness of the supply chain.

[0153] Embodiment 2:

[0154] See also Figure 4 A cargo handling logistics information management method based on big data is operated based on the cargo handling logistics information management system based on big data described in Example 1, and includes the following specific steps:

[0155] S1. Data collection;

[0156] Collect historical loading and unloading data, real-time traffic data, weather information, sensor data, and biometric data to build a data warehouse;

[0157] S2, data preprocessing;

[0158] Clean, deduplicate and format the collected data to ensure data integrity and consistency;

[0159] S3. Demand forecasting;

[0160] Use the intelligent forecasting module to apply time series analysis and regression models to predict future cargo handling needs and transportation times;

[0161] S4, path optimization;

[0162] Apply ant colony algorithm to optimize loading and unloading routes to minimize transportation time and cost, while dynamically updating routes to cope with emergencies;

[0163] S5. Security monitoring;

[0164] Implementing an intelligent safety monitoring module that monitors loading and unloading operations in real time through video surveillance and sensor technology, and uses deep learning algorithms to identify abnormal behavior;

[0165] S6. Dynamic inventory management;

[0166] Dynamically adjust inventory levels and optimize resource allocation based on real-time data and demand forecasts;

[0167] S7, supply chain collaboration;

[0168] Through the supply chain collaboration module, upstream and downstream data are integrated to promote information sharing and decision-making collaboration, thereby improving overall operational efficiency.

[0169] Through the above steps, an efficient and intelligent cargo loading and unloading logistics information management system is formed to improve the safety and efficiency of logistics management.

[0170] The beneficial effects of the present invention are:

[0171] This cargo loading and unloading logistics information management system and method based on big data can analyze and process data in real time, thereby improving the safety and efficiency of overall logistics operations, reducing transportation costs, and realizing intelligent management. Through accurate demand forecasting and dynamic path optimization, it can reduce transportation time and costs. At the same time, real-time safety monitoring will reduce the probability of accidents and protect the safety of employees and assets.

[0172] In the description of this specification, the description with reference to the terms "one embodiment", "some embodiments", "example", "specific example", or "some examples" etc. means that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present invention. In this specification, the schematic representations of the above terms do not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described may be combined in any one or more embodiments or examples in a suitable manner. In addition, those skilled in the art may combine and combine the different embodiments or examples described in this specification and the features of the different embodiments or examples, without contradiction.

[0173] Although embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that various changes, modifications, substitutions and variations may be made to the embodiments without departing from the principles and spirit of the present invention, and that the scope of the present invention is defined by the appended claims and their equivalents.

Claims

1. A cargo loading and unloading logistics information management system based on big data, characterized in that: It includes intelligent cargo tracking module, intelligent prediction module, optimized loading and unloading path module, intelligent safety monitoring module, dynamic inventory management module and supply chain collaboration module; The intelligent cargo tracking module uses the Internet of Things technology and RFID tags to monitor and track each piece of cargo during the loading and unloading process in real time, and the location information and status of the cargo can be viewed in real time through a mobile phone or computer; The intelligent prediction module uses big data data mining technology to analyze historical loading and unloading data based on machine learning, and generates accurate demand forecasts by comprehensively analyzing factors such as weather, traffic conditions and holidays; The loading and unloading path optimization module optimizes the loading and unloading path using an algorithm and dynamically adjusts the optimal path based on real-time updated traffic data and equipment status; The intelligent safety monitoring module monitors the potential safety hazards in the loading and unloading process in real time based on video monitoring and sensor networks, and uses deep learning algorithms to automatically identify abnormal behaviors and issue alarms in a timely manner; The dynamic inventory management module monitors and adjusts inventory status through real-time data analysis; The supply chain collaboration module integrates data from all parties to collaborate with upstream and downstream parties in the supply chain, and automates cargo loading and unloading contract execution and fee payment by sharing data and using smart contracts.

2. A cargo handling logistics information management system based on big data according to claim 1, characterized in that: The intelligent cargo tracking module uses blockchain technology to store all the transfer information of the cargo during the loading and unloading process, ensuring that the data during the cargo loading and unloading process cannot be tampered with.

3. The cargo handling logistics information management system based on big data according to claim 1 is characterized in that: The intelligent prediction module uses a combination of time series analysis and regression model to predict future cargo handling demand and transportation time; By using the ARIMA model or SARIMA model, the intelligent forecasting module captures the seasonal fluctuations and long-term trends of historical demand, identifies cyclical changes by analyzing the autocorrelation of cargo handling data, and predicts future demand. A multivariate regression model is established, with historical demand as the dependent variable and weather, traffic conditions, and holidays as independent variables, to output forecasts of future cargo handling demand and transportation time.

4. A cargo handling logistics information management system based on big data according to claim 3, characterized in that: The multivariate regression model is shown below: Y=β0+β1X1+β2X2+...+β n X n +∈; in, Y is the dependent variable, i.e. the target variable, such as cargo handling demand or transportation time; X1, X2, ..., X n are independent variables, i.e. characteristic variables, such as weather, traffic conditions, and holiday factors; β0 is the intercept, i.e. the constant term, which represents the value of the dependent variable when the independent variable is zero; β1, β2, ..., β n is the regression coefficient, which indicates the influence of the independent variable on the dependent variable; ∈ is the error term.

5. A cargo handling logistics information management system based on big data according to claim 4, characterized in that: The multivariate regression model includes the following processes when predicting future cargo handling demand and transportation time: Data preparation: Collect and organize historical loading and unloading data, including cargo loading and unloading demand, transportation time, and related independent variables such as weather, traffic conditions, and holiday factors; Model training: The historical loading and unloading data are divided into a training set and a test set. The training set is used to fit the multivariate regression model, and the regression coefficients β1, β2, ..., β n ; Model validation: Use the test set to evaluate the performance of the multivariate regression model and calculate the prediction error to verify the accuracy of the multivariate regression model. If the model performs well, it is directly used for prediction. Future prediction: Collect future independent variable data, such as expected weather, traffic conditions, and holiday factors. The data is obtained through weather forecasts and traffic flow forecasts. Substitute the independent variables into the trained multivariate regression model and calculate the predicted value Y, then: Y 预测 =β0+β1X 1,未来 +β2X 2,未来 +…+b n X n，未来 ; Output: Generate forecasts of future cargo handling demand and transportation time to help logistics companies allocate resources and adjust cargo handling plans.

6. A cargo handling logistics information management system based on big data according to claim 1, characterized in that: The loading and unloading path optimization module performs path optimization based on an ant colony algorithm, and the algorithm includes the following construction steps: First, the path is constructed. Each ant randomly selects a path. The path selection probability is determined by pheromone and heuristic information: Among them, τ ij is the pheromone intensity, η ij is heuristic information, such as the inverse of the distance, and α and β are weight parameters; Secondly, pheromone is updated according to the path quality of the ants: t ij =(1-ρ)τ ij +△τ ij ; Where ρ is the volatility, Δτ ij is the contribution of the path, a function of path quality and length; Finally, iterations are performed to repeat path construction and pheromone updating until a termination condition is reached, such as reaching the optimal solution or the number of iterations.

7. A cargo handling logistics information management system based on big data according to claim 6, characterized in that: The loading and unloading path optimization module optimizes the cargo loading and unloading path based on the ant colony algorithm, including the following processes: Determine loading and unloading points: List all loading and unloading points that need to be visited, such as warehouses, ports, and distribution centers, and clearly define optimization goals, such as minimizing transportation time and cost or maximizing loading efficiency; Initialize parameters: set the number of ants, set pheromones and heuristic factors, and define the parameters; Cargo loading and unloading path construction: Each ant starts from the starting point, selects the next loading and unloading point based on the selection probability, combined with pheromone and heuristic information, and updates the visited path until all loading and unloading points are visited and return to the starting point; Pheromone update: Calculate the quality of the path taken by each ant, such as transportation time and cost, and update the pheromone according to the path quality, Δτ ij Proportional to the quality of the path; Iteration: Perform multiple iterations, allowing ants to continuously explore new paths and update pheromones, and monitor the best path and corresponding quality of each iteration; Set termination conditions: reaching the maximum number of iterations, the path quality change is less than the set threshold in multiple iterations, and a path that meets the optimization goal is found; Result output: record the best path found during the iteration process and its corresponding transportation time and cost, and visualize the path; Dynamic adjustment: Regularly update traffic data and weather conditions, dynamically adjust pheromones, and re-run the ant colony algorithm based on new data to ensure that the path optimization matches the real-time situation.

8. The cargo handling logistics information management system based on big data according to claim 1, characterized in that: The abnormal behavior scoring model is constructed in the intelligent security monitoring module, including the following processes: Input data, including video stream data V t : Video frame at time t; sensor data S t : Real-time sensor parameters including temperature, humidity, and location; biometric data B t : Employees’ biometric data, such as facial recognition, fingerprints; Output result, output abnormal behavior score A t : reflects whether the operation at the current time t is normal; Design an abnormal behavior scoring model and integrate multiple features. The model is as follows: A t =f(V t ,S t ,B t )=w1·F V (V t )+w2·F S (S t )+w3·F B (B t ); in, F V (V t ) is a deep learning feature extraction function based on video stream data, which uses a convolutional neural network (CNN) to extract behavioral features in key frames, expressed as: F V (V t )=CNN(V t ); F S (B t ) is the feature extraction based on sensor data, and the state change features are extracted using the time series analysis method, which is expressed as: F S (S t )=TS(S t ); F B (B t ) is a feature extraction based on biometric data, using a classification algorithm such as a support vector machine or a random forest to determine the compliance of the operation, expressed as: F B (B t )=Classifier(B t ); w1, w2, and w3 are weight coefficients, reflecting the importance of different features in abnormal behavior scoring; Determine abnormal behavior. When the score is A t When a certain threshold value T is exceeded, an alarm is issued.

9. The cargo handling logistics information management system based on big data according to claim 1, characterized in that: The dynamic inventory management module also automatically adjusts inventory levels based on the inflow and outflow of goods, demand forecasts and market changes, reduces inventory costs and improves turnover; It also has a built-in intelligent replenishment algorithm that combines big data analysis to predict the best time to replenish and prevent out-of-stock or overstocking.

10. A cargo handling logistics information management method based on big data, operated based on the cargo handling logistics information management system based on big data according to any one of claims 1 to 9, characterized in that: The specific steps include: S1. Data collection; Collect historical loading and unloading data, real-time traffic data, weather information, sensor data, and biometric data to build a data warehouse; S2, data preprocessing; Clean, deduplicate and format the collected data to ensure data integrity and consistency; S3. Demand forecasting; Use the intelligent forecasting module to apply time series analysis and regression models to predict future cargo handling needs and transportation times; S4, path optimization; Apply ant colony algorithm to optimize loading and unloading routes to minimize transportation time and cost, while dynamically updating routes to cope with emergencies; S5. Security monitoring; Implementing an intelligent safety monitoring module that monitors loading and unloading operations in real time through video surveillance and sensor technology, and uses deep learning algorithms to identify abnormal behavior; S6. Dynamic inventory management; Dynamically adjust inventory levels and optimize resource allocation based on real-time data and demand forecasts; S7, supply chain collaboration; Through the supply chain collaboration module, upstream and downstream data are integrated to promote information sharing and decision-making collaboration, thereby improving overall operational efficiency.

Images