An artificial intelligence-based method and system for logistics cargo transportation scheduling

Abstract

The present invention relates to the technical field of logistics management, and in particular to a logistics goods transportation scheduling method and system based on artificial intelligence. The method includes the following steps: obtaining logistics node data; performing multi-dimensional logistics data collection on the logistics node data to generate multi-dimensional logistics data; constructing a logistics monitoring network based on the logistics node data as nodes and the multi-dimensional logistics data to generate a logistics monitoring network, where the logistics monitoring network includes warehousing node, distribution center node and transportation tool node; performing data preprocessing on the multi-dimensional logistics data through the logistics monitoring network to generate standard multi-dimensional logistics monitoring data; searching for the positions of adjacent logistics warehousing nodes for the standard multi-dimensional logistics monitoring data through the distribution center node to generate adjacent warehousing node position information data. The present invention improves the efficiency and reliability of logistics goods scheduling through multi-dimensional data collection, dynamic path optimization, delay prediction and full-link feedback mechanism.

Description

Technical Field

[0001] The present invention relates to the technical field of logistics management, and in particular, to a logistics goods transportation scheduling method and system based on artificial intelligence. Background Art

[0002] Early scheduling methods mainly relied on manual experience and lacked systematicness and efficiency. With the development of information technology, computer-based scheduling systems began to emerge, using simple algorithms for cargo allocation and route planning. However, due to the limitations of computing power, the application effects of these systems were limited. Entering the 21st century, the development of the Internet of Things (IoT) enabled real-time monitoring of the transportation process in logistics management. Through sensors and GPS technology, logistics companies could obtain the location information of goods in real time, and then optimize scheduling decisions. However, the explosion of data volume also brought new challenges, and traditional algorithms were difficult to handle complex scheduling problems. With the maturity of big data technology, logistics scheduling systems began to introduce data analysis and machine learning technologies. By analyzing historical data, AI could identify transportation patterns and demand fluctuations, so as to predict the best transportation plan. In addition, the application of deep learning algorithms enabled the system to perform more accurate route planning and scheduling decisions. However, the existing technologies at present are often relatively static for route planning, difficult to adjust in real time according to the dynamic data of logistics nodes, and relatively lagging in predicting transportation delays and coping with abnormal situations, thus resulting in low efficiency and reliability of logistics goods scheduling. Summary of the Invention

[0003] Based on this, it is necessary to provide a logistics goods transportation scheduling method and system based on artificial intelligence to solve at least one of the above technical problems.

[0004] To achieve the above object, a logistics goods transportation scheduling method based on artificial intelligence, the method includes the following steps:

[0005] Step S1: Obtain logistics node data; collect multi-dimensional logistics data from the logistics node data to generate multi-dimensional logistics data; construct a logistics monitoring network based on the logistics node data as nodes and the multi-dimensional logistics data to generate a logistics monitoring network, where the logistics monitoring network includes warehousing node, distribution center node and transportation tool node; perform data preprocessing on the multi-dimensional logistics data through the logistics monitoring network to generate standard multi-dimensional logistics monitoring data;

[0006] Step S2: Search for the locations of adjacent logistics warehousing nodes from the standard multi-dimensional logistics monitoring data through the distribution center node to generate adjacent warehousing node location information data; perform initial transportation route planning for the logistics cargo transportation destination data based on the adjacent warehousing node location information data to generate initial logistics cargo transportation planning route data; conduct warehousing scheduling retention analysis on the standard multi-dimensional logistics monitoring data through the warehousing node to generate warehousing scheduling retention data; screen the initial logistics cargo transportation planning route data based on the warehousing scheduling retention data to generate optimized logistics cargo transportation planning route data;

[0007] Step S3: Sort the logistics order data according to the optimized logistics cargo transportation planning route data to generate cargo transportation priority ranking data; confirm the transportation mode based on the cargo transportation priority ranking data to generate a normal cargo transportation scheduling strategy; predict abnormal delay in transportation based on the standard multi-dimensional logistics monitoring data through the transportation vehicle node to generate abnormal delay prediction data; perform multi-modal transportation scheduling for the cargo transportation based on the abnormal delay prediction data to generate cargo transportation multi-modal transportation scheduling data; simulate the multi-modal transportation scheduling data for the cargo transportation to generate cargo transportation multi-modal transportation scheduling simulation data;

[0008] Step S4: Analyze the scheduling transport capacity of the cargo transportation multi-modal transportation scheduling simulation data to generate scheduling transport capacity analysis data; construct a joint scheduling plan for the cargo transportation multi-modal transportation scheduling simulation data based on the scheduling transport capacity analysis data to generate joint scheduling plan data; perform full-link transportation feedback on the logistics monitoring network according to the joint scheduling plan data and the logistics transportation anomaly detection data to generate full-link transportation feedback data for implementing the logistics cargo transportation scheduling operation.

[0009] The present invention ensures the comprehensiveness and diversity of information by acquiring logistics node data and conducting multi-dimensional data collection, enabling subsequent analysis to be based on a richer data foundation. Through the preprocessing of multi-dimensional logistics data, standard multi-dimensional logistics monitoring data is generated, which provides high-quality data support for the subsequent analysis and decision-making of the logistics system and reduces the decision-making risks caused by data inconsistencies. By the distribution center node searching for the positions of adjacent logistics warehousing nodes, the rationality and effectiveness of path planning are ensured. Such operations not only improve the transportation efficiency but also reduce the transportation costs. Based on the retained data of warehouse scheduling, the initial path is screened to ensure the optimization of the transportation path, minimizing the transportation time and resource consumption to the greatest extent. The goods transportation priorities of logistics order data are sorted, making the resource allocation more reasonable, giving priority to meeting the transportation needs of high-priority orders, and enhancing customer satisfaction. Through the analysis of the sorted priority data, a normal goods transportation scheduling strategy is generated, further ensuring the efficiency and adaptability of transportation. Based on the anomaly detection of standard multi-dimensional logistics monitoring data, the system's ability to predict potential transportation delays is improved, identifying transportation problems in advance, helping managers adjust the scheduling plan in a timely manner, and reducing the negative impacts brought by delays. Through the multi-modal transport scheduling of goods transportation based on the anomaly delay prediction data, the use of transportation resources is optimized, the flexible switching of transportation modes is realized, and different transportation needs are adapted. The generation and analysis of the multi-modal transport scheduling simulation data enable the prediction and adjustment of the effects of the scheduling plan before implementation, reducing the risks in actual operations. Through the analysis of the scheduling simulation data, the utilization rate of transportation resources can be evaluated and optimized in real time, ensuring the rationality of the transport capacity configuration and enhancing the efficiency of logistics operations. By combining the joint scheduling plan data with the logistics transportation anomaly detection data, full-link transportation feedback data is generated, making the information of each link in the logistics transportation transparent, facilitating managers to adjust strategies in a timely manner, and enhancing the overall logistics efficiency. This method provides effective data support for decision-makers by constructing a systematic logistics monitoring network and an intelligent data processing mechanism, making the decision-making process more scientific and accurate. In a constantly changing market environment, the scheduling method based on artificial intelligence can quickly adapt to new situations, ensure the efficient operation of the logistics system, and has strong adaptability. Therefore, the present invention improves the efficiency and reliability of logistics goods scheduling through multi-dimensional data collection, dynamic path optimization, delay prediction, and full-link feedback mechanism.

[0010] Preferably, step S1 includes the following steps:

[0011] Step S11: Acquire logistics node data;

[0012] Step S12: Use edge computing network technology to deploy sensing devices for the logistics node data to obtain logistics node sensing device deployment data; conduct multi-dimensional logistics data collection on the logistics node sensing device deployment data to generate multi-dimensional logistics data;

[0013] Step S13: Use the logistics node data as nodes and the multi-dimensional logistics data as edges to construct a logistics monitoring network, generating a logistics monitoring network, where the logistics monitoring network includes warehouse nodes, distribution center nodes, and transportation tool nodes;

[0014] Step S14: Perform data preprocessing on the multi-dimensional logistics data through the logistics monitoring network to generate standard multi-dimensional logistics monitoring data, where the data preprocessing includes data cleaning, data denoising, data normalization, and data standardization.

[0015] The present invention realizes real-time monitoring of all links of logistics by constructing a logistics monitoring network including warehouse nodes, distribution center nodes, and transportation tool nodes, which enables managers to timely discover and handle anomalies in the logistics process, optimize the logistics path, and improve transportation efficiency. Multidimensional data of logistics nodes are collected by using sensing devices, and through data preprocessing steps (such as cleaning, denoising, normalization, and standardization), the accuracy and consistency of logistics data are ensured, providing reliable basic data for subsequent analysis and decision-making. The application of edge computing network technology enables the sensing devices to perform calculations and processing close to the data source, reducing the data transmission delay and improving the system response speed, which helps to realize a more intelligent and real-time logistics monitoring and management system. The logistics monitoring network can adapt to different scales and types of logistics scenarios through flexible configuration of nodes and edges. Whether it is a large-scale warehouse network or a multi-node transportation and distribution chain, it can effectively operate under this network architecture, enhancing the scalability and flexibility of the system. Through the standardized multi-dimensional logistics monitoring data, not only the data quality is improved, but also a consistent data basis can be provided for the collaborative operation of multiple systems, promoting seamless docking and collaboration between different logistics management systems or platforms.

[0016] Preferably, step S2 includes the following steps:

[0017] Step S21: Extract logistics order data from the standard multi-dimensional logistics monitoring data through the distribution center node, obtaining logistics order data; perform destination analysis on the logistics order data to generate logistics cargo transportation destination data;

[0018] Step S22: Search for the positions of adjacent warehouse nodes for the logistics cargo transportation destination data to generate adjacent warehouse node position information data; perform initial transportation path planning on the logistics cargo transportation destination data through the adjacent warehouse node position information data to generate initial logistics cargo transportation planning path data;

[0019] Step S23: Extract the storage space of the standard multi-dimensional logistics monitoring data through the warehousing node to obtain the warehousing storage space data; perform an available space analysis on the warehousing storage space data to generate the available data of the warehousing storage space.

[0020] Step S24: Perform a warehousing scheduling retention analysis on the available data of the warehousing storage space to generate the warehousing scheduling retention data; based on the warehousing scheduling retention data, perform a path screening on the initial logistics cargo transportation planning path data to generate the optimized path data for the logistics cargo transportation planning.

[0021] Through the extraction of logistics order data and destination analysis, the present invention ensures the accurate positioning of the destination of each batch of goods, making the logistics distribution process more efficient and reducing the delay or loss of goods caused by incorrect destinations. Based on the location information of adjacent warehousing nodes, the initial transportation path planning can effectively reduce the transportation distance and time, optimizing the logistics cost. In addition, through subsequent path screening, the transportation path is further optimized to ensure that the goods are delivered on the optimal route, improving the overall logistics efficiency. By using the extraction of warehousing storage space data and available space analysis, the warehousing node can grasp the currently available storage resources in real time, avoiding the situation of insufficient or wasted warehousing space, which helps the reasonable allocation and efficient utilization of warehousing resources. The warehousing scheduling retention analysis can effectively avoid the overstocking or ineffective mobilization of goods through the dynamic management of the storage space, improving the operating efficiency of the warehousing node. This scheduling optimization further affects the screening of the cargo transportation path, ensuring the close cooperation between warehousing and transportation. Step S2 realizes the full-process optimization from order generation to transportation and distribution through the collaborative work of multiple links such as order extraction, destination analysis, warehousing scheduling, and path optimization, improving the overall efficiency of the logistics system, reducing costs, and improving service quality. Through the optimization and screening of the transportation path, combined with the effective scheduling of warehousing resources, unnecessary intermediate links and resource waste are significantly reduced, thereby shortening the transportation time and reducing the logistics cost.

[0022] Preferably, step S24 includes the following steps:

[0023] Step S241: Perform a temporal trend analysis of the available space on the available data of the warehousing storage space to generate the temporal trend data of the available space; perform a curve conversion on the temporal trend data of the available space to generate the temporal trend curve of the available space.

[0024] Step S242: Calculate the curve curvature of the temporal trend curve of the available space to obtain the available curvature data of the warehousing space; perform a positive and negative value discrimination on the available curvature data of the warehousing space. When the available curvature data of the warehousing space is positive, mark the corresponding warehousing node as a crowded state based on the available curvature data of the warehousing space to generate the crowded warehousing node data.

[0025] Step S243: When the available curvature data of the storage space is negative, the corresponding storage nodes are marked as idle based on the available curvature data of the storage space to generate idle storage node data; the initial logistics cargo transportation planning path data is screened for the first time according to the crowded storage node data and the idle storage node data, and the crowded storage node data is excluded to generate the screened path of the logistics cargo transportation planning.

[0026] Step S244: The available data of the storage space is analyzed for storage scheduling retention according to the idle storage node data to generate storage scheduling retention data; the initial logistics cargo transportation planning path data is screened based on the storage scheduling retention data to generate the optimized path data of the logistics cargo transportation planning.

[0027] Through the time-series trend analysis of the available data of the storage space, the present invention can predict the change trend of the storage space in advance, and judge the positive and negative values according to the curvature data of the storage space to mark the crowded state or idle state of the storage nodes, so as to allocate and schedule resources in a targeted manner and maximize the utilization rate of the storage resources. The generation of the available time-series trend curve of the space and the curvature calculation enable the system to monitor the state of the storage nodes in real time. Through the crowded state marking and idle state marking, the logistics system can immediately understand the usage situation of each storage node and quickly adjust the storage scheduling plan. Through the first path screening, the crowded storage nodes are excluded to avoid delays caused by insufficient storage resources or congestion of goods, ensuring that the nodes passed by the transportation path have sufficient storage space when the goods arrive, which effectively reduces the potential delay risk during transportation and improves the transportation efficiency. The storage scheduling retention analysis further evaluates the available space of the idle storage nodes, enabling the storage scheduling plan to be dynamically adjusted according to the actual situation, ensuring that the load of the storage nodes is within a reasonable range and avoiding waste or overload of the storage resources. The available time-series trend analysis of the space and the curvature calculation provide key data support for the logistics system, helping the system make more intelligent decisions in path planning and storage scheduling. This data-driven decision-making mechanism effectively improves the overall response speed and accuracy of the logistics chain. Through the optimized screening of the path and the intelligent scheduling of the storage nodes, the additional transportation and storage costs caused by storage congestion or improper scheduling are avoided, and the efficiency and economy of the entire logistics process are improved.

[0028] Preferably, step S3 includes the following steps:

[0029] Step S31: Extract the logistics cargo characteristics from the logistics order data to obtain the logistics cargo characteristic data; evaluate the importance of the cargo for the logistics cargo characteristic data to generate the cargo importance evaluation data; sort the logistics order data according to the optimized path data of the logistics cargo transportation based on the cargo importance evaluation data to generate the cargo transportation priority sorting data.

[0030] Step S32: Confirm the transportation mode according to the sorted data of the cargo transportation priority, and generate a normal cargo transportation scheduling strategy; extract transportation data from the standard multi-dimensional logistics monitoring data based on the transportation tool node through the normal cargo transportation scheduling strategy to obtain logistics transportation data;

[0031] Step S33: Detect transportation anomalies in the logistics transportation data to generate logistics transportation anomaly detection data; predict abnormal delays for the logistics order data based on the logistics transportation anomaly detection data to generate abnormal delay prediction data;

[0032] Step S34: Conduct multi-modal transportation scheduling for the logistics transportation data through the abnormal delay prediction data to generate multi-modal transportation scheduling data for cargo transportation; simulate the multi-modal transportation scheduling data for cargo transportation to generate multi-modal transportation scheduling simulation data for cargo transportation.

[0033] Through the feature extraction and importance assessment of logistics goods, the present invention can accurately determine the transportation priority of each batch of goods and generate sorted data of cargo transportation priority, which helps to reasonably arrange the transportation sequence, ensure that urgent goods or high-value goods are processed first, and optimize the allocation of logistics resources. Confirming the transportation mode based on the sorted data of cargo transportation priority makes the transportation scheduling more flexible. For example, important goods can preferentially choose faster or safer transportation modes, while ordinary goods can choose lower-cost modes, thereby achieving the rational utilization of resources. By real-time monitoring and anomaly detection of the logistics transportation data, problems occurring during the transportation process can be quickly discovered, and abnormal delays of the logistics orders can be predicted based on the detection results, which helps to early warn of potential delay risks, enabling logistics managers to take corresponding measures in a timely manner and reduce the impact of delays. According to the abnormal delay prediction data, multi-modal transportation scheduling is performed on the logistics transportation to achieve the coordinated operation between different transportation modes. The multi-modal transportation scheduling data enables the system to select the optimal transportation combination according to the actual situation, reducing the delays and increased costs caused by the limitation of a single transportation mode. Through the simulation of multi-modal transportation scheduling, the feasibility and effects of different scheduling strategies can be pre-evaluated, which not only improves the accuracy of logistics scheduling, but also optimizes the logistics route and transportation mode in advance, avoiding delays or waste of resources caused by incorrect scheduling strategies. Step S3 optimizes the entire process from cargo priority sorting, transportation mode confirmation, anomaly detection to multi-modal transportation scheduling, forming a complete logistics management closed loop. Data-driven decision-making in each link can effectively improve the overall efficiency and response speed of the logistics chain and reduce the operating costs.

[0034] Preferably, step S33 includes the following steps:

[0035] Step S331: Confirm the transportation location coordinates of the logistics transportation data to obtain the logistics transportation location coordinates; update the coordinates of the logistics transportation location coordinates based on a preset time interval to generate updated logistics transportation location coordinates;

[0036] Step S332: Construct a coordinate movement trajectory for the logistics transportation location coordinates and the updated logistics transportation location coordinates to generate coordinate update trajectory data; discretize the coordinate update trajectory data to generate coordinate update trajectory discrete points; calculate the distance between adjacent discrete points of the coordinate update trajectory discrete points to obtain coordinate update discrete point distance data;

[0037] Step S333: Compare the coordinate update discrete point distance data with a preset discrete point distance threshold. When the coordinate update discrete point distance data is less than the preset discrete point distance threshold, mark the corresponding coordinate update trajectory data as abnormal coordinate trajectory data;

[0038] Step S334: Perform transportation anomaly detection on the logistics transportation data based on the abnormal coordinate trajectory data to generate logistics transportation anomaly detection data; divide the logistics transportation anomaly detection data into a dataset to generate a model training set and a model test set; train the model training set through a long short-term memory network algorithm to generate an abnormal delay prediction pre-model;

[0039] Step S335: Optimize and iterate the abnormal delay prediction pre-model through the model test set to generate an abnormal delay prediction model; import the logistics transportation anomaly detection data and the logistics order data into the abnormal delay prediction model for abnormal delay prediction to generate abnormal delay prediction data.

[0040] Through the confirmation of the transportation position coordinates and the update of coordinates within a preset time interval, the system can track the transportation position of goods in real time. This helps to ensure that every link in the logistics chain can obtain the latest transportation information in a timely manner, thereby improving the real-time performance and accuracy of logistics monitoring. Through the construction and discretization of the logistics transportation position trajectory, the system can accurately calculate the distance between adjacent discrete points and monitor the deviation of the goods transportation trajectory in real time. When the transportation trajectory shows an anomaly, the system can immediately mark it and generate anomaly coordinate trajectory data to provide data support for subsequent anomaly detection and delay prediction. Based on the comparison between the distance of discrete points and a preset threshold, the system can quickly identify abnormal transportation trajectories that cause delays or risks. Marking these abnormal trajectories helps logistics managers to promptly discover potential problems in transportation and avoid delays or damages. Through the Long Short-Term Memory (LSTM) algorithm, the system can model the transportation anomaly detection data and train an anomaly delay prediction model. The LSTM algorithm is good at processing time series data and can accurately predict future delay risks based on the change trends of historical trajectories and transportation data. By dividing the dataset and optimizing and iterating the model, the anomaly delay prediction model can continuously improve according to actual logistics data, enhancing the accuracy and reliability of the prediction. Through the optimization and iteration of the model, the system can better cope with complex and ever-changing logistics transportation environments. The introduction of the anomaly delay prediction model enables the system to anticipate delay problems that occur during transportation in advance, thus providing sufficient time for logistics managers to take countermeasures. Through accurate delay prediction, the system can optimize logistics scheduling and avoid additional costs and a decline in customer satisfaction caused by delays. From the construction of the transportation trajectory, the calculation of discrete points to the delay prediction based on LSTM, the entire step S33 is a data-driven intelligent logistics management process. This process not only improves the accuracy of logistics monitoring but also greatly enhances the prediction ability and response ability in logistics transportation through machine learning algorithms.

[0041] Preferably, step S34 includes the following steps:

[0042] Step S341: Analyze the initial transportation mode of the logistics transportation data to generate initial transportation mode data; segment the delay sections of the logistics transportation data through the anomaly delay prediction data to generate delay section segmentation data;

[0043] Step S342: Conduct an intermodal mode matching analysis on the delay section segmentation data to generate multimodal transportation feasibility data, where the intermodal modes include land transportation, sea transportation, air transportation, and rail transportation; allocate transportation resources to the delay section segmentation data according to the multimodal transportation feasibility data to generate goods transportation multimodal transportation scheduling data;

[0044] Step S343: Reconstruct the path of the delay section segmentation data according to the goods transportation multimodal transportation scheduling data to generate multimodal transportation reconstructed path data;

[0045] Step S344: Schedule and simulate the delay section segmentation data through the multimodal transport reconstructed path data to generate the multimodal transport scheduling simulation data for cargo transportation.

[0046] Through the analysis of the initial transportation mode of the logistics transportation data, the present invention can quickly generate the initial transportation mode data, and combine the abnormal delay prediction data to segment the delay sections. This segmented analysis enables the system to accurately identify the sections that cause delays during the transportation process, which helps logistics managers formulate targeted countermeasures. After identifying the delay sections, the system evaluates the feasibility of multimodal transport such as land transport, sea transport, air transport, and rail transport through the multimodal transport mode matching analysis. Based on the multimodal transport feasibility data, the system can dynamically allocate the transportation resources for the delay sections to ensure the selection of the best combination of transportation modes in the shortest time, thus improving the transportation efficiency. By reconstructing the path of the delay section segmentation data through the multimodal transport scheduling data, a more efficient multimodal transport reconstructed path is generated. This step effectively solves the problem of inefficient path caused by the delay section during the transportation process, provides an optimized transportation path for the smooth transportation of goods, and reduces the risk brought by delays. By scheduling and simulating the multimodal transport reconstructed path data, it is possible to evaluate in advance the actual effects of different transportation modes and path combinations, generate the multimodal transport scheduling simulation data. This simulation process helps the system discover potential problems in advance and provides a reliable basis for the final transportation scheduling decision, further reducing the operation risk. Step S34 enables the logistics system to flexibly adjust the transportation plan in a complex transportation environment through the segmentation of the delay section, multimodal transport feasibility analysis, path reconstruction, and simulation. This not only improves the flexibility of transportation scheduling but also enhances the logistics management's ability to respond to emergencies. The introduction of multimodal transport and the optimized allocation of resources enable the logistics system to make more efficient use of various transportation resources, reducing delays and additional costs caused by a single transportation mode or improper path selection. In addition, the scheduling simulation process can identify potential delay risks in advance, thus effectively reducing unnecessary losses during the transportation process.

[0047] Preferably, step S4 includes the following steps:

[0048] Step S41: Extract the scheduling delivery time from the multimodal transport scheduling simulation data for cargo transportation to generate the scheduling delivery time data; conduct scheduling capacity analysis on the scheduling delivery time data and the abnormal delay prediction data to generate the scheduling capacity analysis data;

[0049] Step S42: Construct a joint scheduling plan for the multimodal transport scheduling simulation data for cargo transportation through the scheduling capacity analysis data to generate the joint scheduling plan data;

[0050] Step S43: Match the joint scheduling plan data with the logistics transportation anomaly detection data to generate an abnormal transportation joint scheduling strategy; based on the normal cargo transportation scheduling strategy and the abnormal transportation joint scheduling strategy, perform full-link transportation feedback on the logistics monitoring network to generate full-link transportation feedback data for executing the logistics cargo transportation scheduling operation.

[0051] The present invention extracts the scheduling delivery time from the scheduling simulation data of multimodal transportation of cargo to generate scheduling delivery time data. These data are combined with the abnormal delay prediction data for scheduling capacity analysis to ensure that the system can perform reasonable capacity planning and allocation for transportation demands, improving transportation efficiency and reducing resource waste. Based on the scheduling capacity analysis data, the system can construct a joint scheduling plan for multimodal transportation. The joint scheduling plan data not only cover the coordination and cooperation between different transportation modes but also can handle emergencies occurring during transportation, providing a flexible and efficient transportation scheduling solution. By matching the joint scheduling plan data with the logistics transportation anomaly detection data, an abnormal transportation joint scheduling strategy is generated. This strategy can be coordinated with the conventional cargo transportation scheduling strategy to ensure that in the logistics chain, both regular transportation tasks can be handled and abnormal transportation situations can be quickly responded to, thereby improving the overall contingency ability of the logistics system. Through the generation of full-link transportation feedback data, the logistics system can monitor the transportation conditions of the entire logistics chain in real time according to the normal and abnormal transportation scheduling strategies and make dynamic adjustments. This full-link feedback mechanism enhances the transparency and controllability of logistics transportation, ensures the efficient operation of each link, and reduces the risk of transportation delays or interruptions. By combining multi-dimensional data such as multimodal transportation scheduling simulation, capacity analysis, abnormal delay prediction, and full-link feedback, an intelligent logistics scheduling execution plan is provided. The system can dynamically adjust the scheduling strategy according to real-time data and predictive analysis to ensure the smoothness and punctuality of cargo transportation and improve the overall operation efficiency of the logistics system. Through scheduling capacity analysis and the construction of an abnormal joint scheduling strategy, the system can foresee potential delay risks during transportation and take measures in advance for optimization, minimizing the impact of delays. In addition, reasonable scheduling capacity analysis ensures the full utilization of logistics resources, avoids problems caused by overcapacity or insufficient capacity, and optimizes the resource allocation of the logistics system. Through the construction of a joint scheduling plan and the full-link feedback mechanism, the coordination of each link in logistics has been significantly improved. The collaborative operation between different nodes and transportation modes ensures seamless connection of the entire process from warehousing to transportation and then to distribution, improving the overall operation efficiency of the entire logistics system. The combination of the joint scheduling strategy and the abnormal scheduling strategy makes the logistics system more robust in dealing with sudden abnormal situations. Whether it is a delay during transportation, equipment failure, or traffic congestion, the system can quickly respond and adjust the transportation plan, ensuring the continuity and stability of the logistics chain.

[0052] Preferably, step S41 includes the following steps:

[0053] Step S411: Extract time nodes from the multimodal transport scheduling simulation data of goods transportation to generate scheduling time node data; calculate the delivery time for the scheduling time node data to generate scheduling delivery time data;

[0054] Step S412: Compare the scheduling delivery time data with the abnormal delay prediction data to generate time difference analysis data; conduct a transport capacity scheduling analysis on the time difference analysis data to generate preliminary scheduling transport capacity analysis data, where the transport capacity scheduling analysis formula is specifically as follows:

[0055]

[0056] In the formula, U represents the transport capacity utilization rate, D represents the transport demand, C represents the available transport capacity, E represents the scheduling efficiency factor, T d represents the actual delay time, and T s represents the scheduled delivery time;

[0057] Step S413: Optimize the transport capacity for the preliminary scheduling transport capacity analysis data to generate scheduled transport capacity optimization data; conduct a clustering analysis of the actual transport situation on the scheduled transport capacity optimization data to generate scheduled transport capacity analysis data.

[0058] Through the extraction of time nodes from the scheduling simulation data and the calculation of delivery times, the present invention generates accurate scheduling delivery time data, which provides a basis for subsequent delay warnings and optimizations, ensuring that the logistics system can precisely control the time progress of each transportation link, thereby improving the punctuality and reliability of deliveries. By comparing the scheduling delivery time data with the abnormal delay prediction data, the system generates time difference analysis data, which enables the system to anticipate potential delay problems in advance and conduct timely analysis of transportation capacity scheduling, thus effectively reducing the negative impacts caused by delays. The application of the formula enables the system to scientifically evaluate the utilization rate of transportation capacity and ensure the maximization of its utility under limited transportation resources. Through the optimization of the preliminary scheduling transportation capacity analysis data to generate scheduling transportation capacity optimization data and the clustering analysis of the actual transportation situation, this optimization and clustering analysis can identify the transportation capacity requirements and performance of different transportation plans, thereby providing more accurate data support for subsequent scheduling strategies, which greatly enhances the system's ability to cope with changing transportation environments. Especially in the face of peak logistics periods or abnormal situations, it can dynamically adjust the allocation of transportation capacity to ensure the smooth progress of logistics transportation. Through precise transportation capacity scheduling analysis and optimization, the system can conduct scheduling optimizations in advance when the delay risk is relatively high, ensuring the reasonable allocation of transportation capacity under limited resources, thereby reducing the likelihood of delays. This not only improves the overall transportation efficiency of the logistics system but also reduces customer complaints and resource waste caused by delays. By combining the scheduling delivery time with the abnormal prediction data, the system realizes intelligent transportation capacity management. Based on the real-time generated transportation capacity analysis data, the system can dynamically adjust the scheduling plan to ensure that the cargo transportation is completed within the optimal time, enhancing the flexibility and intelligence level of the logistics system. Step S41 establishes a full-process control system from time node extraction, time difference analysis to transportation capacity scheduling optimization. The data flow of each link is closely connected, enabling the system to comprehensively control the time and transportation capacity during the transportation process and ensuring the stability and efficiency of logistics transportation.

[0059] In this specification, a logistics cargo transportation scheduling system based on artificial intelligence is provided for implementing the above-mentioned logistics cargo transportation scheduling method based on artificial intelligence. The logistics cargo transportation scheduling system based on artificial intelligence includes:

[0060] A logistics network construction module, configured to obtain logistics node data; perform multi-dimensional logistics data collection on the logistics node data to generate multi-dimensional logistics data; construct a logistics monitoring network based on the logistics node data as nodes and the multi-dimensional logistics data to generate a logistics monitoring network, where the logistics monitoring network includes warehousing node, distribution center node, and transportation tool node; perform data preprocessing on the multi-dimensional logistics data through the logistics monitoring network to generate standard multi-dimensional logistics monitoring data;

[0061] The path planning module is used to search for the positions of adjacent logistics storage nodes in the standard multi-dimensional logistics monitoring data through the distribution center node, and generate the position information data of adjacent storage nodes; perform initial transportation path planning on the logistics cargo transportation destination data through the position information data of adjacent storage nodes, and generate the initial logistics cargo transportation planning path data; perform warehousing scheduling retention analysis on the standard multi-dimensional logistics monitoring data through the storage node, and generate the warehousing scheduling retention data; screen the initial logistics cargo transportation planning path data based on the warehousing scheduling retention data, and generate the optimized path data for logistics cargo transportation planning.

[0062] The transportation scheduling module is used to sort the priorities of cargo transportation for the logistics order data according to the optimized path data for logistics cargo transportation planning, and generate the priority sorting data for cargo transportation; confirm the transportation mode according to the priority sorting data for cargo transportation, and generate the normal cargo transportation scheduling strategy; predict the abnormal delay of transportation based on the transportation tool node for the standard multi-dimensional logistics monitoring data, and generate the abnormal delay prediction data; perform multi-modal transportation scheduling for cargo transportation through the abnormal delay prediction data, and generate the multi-modal transportation scheduling data for cargo transportation; simulate the multi-modal transportation scheduling data for cargo transportation, and generate the simulation data for multi-modal transportation scheduling of cargo transportation.

[0063] The link feedback module is used to analyze the scheduling capacity of the multi-modal transportation scheduling simulation data for cargo transportation, and generate the scheduling capacity analysis data; construct a joint scheduling plan for the multi-modal transportation scheduling simulation data for cargo transportation through the scheduling capacity analysis data, and generate the joint scheduling plan data; perform full-link transportation feedback on the logistics monitoring network according to the joint scheduling plan data and the logistics transportation anomaly detection data, and generate the full-link transportation feedback data to execute the logistics cargo transportation scheduling operation.

[0064] The beneficial effects of the present invention are as follows: By comprehensively acquiring logistics node data, it can ensure that the system has a rich information basis, which is helpful for subsequent analysis and decision-making, generate multi-dimensional logistics data and construct a monitoring network, realize real-time monitoring of warehouses, distribution centers and transportation tools, and improve logistics transparency. Standardize multi-dimensional logistics monitoring data to make it suitable for subsequent analysis, ensure data quality and consistency, and thus improve the accuracy of decision-making. Through adjacent node search, the system can quickly identify the best warehouse location, provide a basis for route planning, reduce transportation time and costs, and the generated initial transportation planning route provides a reasonable transportation plan for logistics goods to ensure that the goods are delivered on time. By analyzing warehouse scheduling data, potential scheduling problems can be identified, which helps to optimize inventory management and resource allocation. Based on the scheduling retention data, route optimization is carried out to ensure the selection of the best transportation route, improve transportation efficiency and customer satisfaction. Prioritize transportation orders so that important orders can be processed in a timely manner and resource utilization is optimized. The normal goods transportation scheduling strategy formulated based on priorities ensures transportation in the most appropriate way and improves the response speed. Predict the risk of transportation delays, take countermeasures in advance, and reduce losses caused by delays. Improve transportation flexibility and efficiency through multimodal transportation scheduling, making the connection between different transportation modes smoother. Simulating the scheduling can evaluate the feasibility of different schemes, optimize the actual scheduling decision-making, and reduce risks. Analyzing the scheduling capacity can identify potential bottlenecks and resource waste, so as to achieve more efficient resource allocation. Generate a joint scheduling plan based on the capacity analysis, enabling multiple transportation links to work in coordination and improving the overall efficiency. Through the full-link transportation feedback, the logistics process can be monitored in real time, strategies can be adjusted in a timely manner, and the smoothness and efficiency of logistics operations can be ensured, improving the adaptability and response speed of the overall supply chain. Therefore, the present invention improves the efficiency and reliability of logistics goods scheduling through multi-dimensional data collection, dynamic path optimization, delay prediction and full-link feedback mechanisms. BRIEF DESCRIPTION OF THE DRAWINGS

[0065] Figure 1 It is a schematic diagram of the step flow of a logistics goods transportation scheduling method based on artificial intelligence;

[0066] Figure 2 For Figure 1 it is a schematic diagram of the detailed implementation steps of step S2 in

[0067] Figure 3 For Figure 1 it is a schematic diagram of the detailed implementation steps of step S3 in

[0068] The realization, functional features and advantages of the object of the present invention will be further described with reference to the embodiments and the accompanying drawings. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0069] The technical method of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all of the embodiments. All other embodiments obtained by those skilled in the art based on the embodiments of the present invention without creative efforts belong to the scope of protection of the present invention.

[0070] In addition, the accompanying drawings are only schematic diagrams of the present invention and are not necessarily drawn to scale. The same reference numerals in the drawings represent the same or similar parts, and thus repeated descriptions thereof will be omitted. Some of the block diagrams shown in the drawings are functional entities and do not necessarily correspond to physically or logically independent entities. The functional entities can be implemented in software form, or in one or more hardware modules or integrated circuits, or in different networks and / or processor methods and / or microcontroller methods.

[0071] It should be understood that although terms such as "first", "second", etc. may be used here to describe each unit, these units should not be limited by these terms. These terms are only used to distinguish one unit from another. For example, without departing from the scope of the exemplary embodiments, the first unit may be referred to as the second unit, and similarly the second unit may be referred to as the first unit. The term "and / or" used here includes any and all combinations of one or more of the listed related items.

[0072] To achieve the above object, please refer to Figures 1 to 3 , a logistics cargo transportation scheduling method based on artificial intelligence, the method comprising the following steps:

[0073] Step S1: Obtain logistics node data; perform multi-dimensional logistics data collection on the logistics node data to generate multi-dimensional logistics data; construct a logistics monitoring network based on the logistics node data as nodes and the multi-dimensional logistics data to generate a logistics monitoring network, where the logistics monitoring network includes a warehousing node, a distribution center node, and a transportation tool node; perform data preprocessing on the multi-dimensional logistics data through the logistics monitoring network to generate standard multi-dimensional logistics monitoring data;

[0074] Step S2: Search for the positions of adjacent logistics warehousing nodes for the standard multi-dimensional logistics monitoring data through the distribution center node to generate adjacent warehousing node position information data; perform initial transportation path planning on the logistics cargo transportation destination data through the adjacent warehousing node position information data to generate initial logistics cargo transportation planning path data; perform warehousing scheduling retention analysis on the standard multi-dimensional logistics monitoring data through the warehousing node to generate warehousing scheduling retention data; perform path screening on the initial logistics cargo transportation planning path data based on the warehousing scheduling retention data to generate optimized logistics cargo transportation planning path data;

[0075] Step S3: Sort the logistics order data according to the optimized path data of the logistics goods transportation plan to generate the goods transportation priority sorting data; confirm the transportation mode according to the goods transportation priority sorting data to generate the normal goods transportation scheduling strategy; predict the abnormal delay of the standard multi-dimensional logistics monitoring data based on the transportation tool node to generate the abnormal delay prediction data; perform the multimodal transportation scheduling of the goods through the abnormal delay prediction data to generate the goods multimodal transportation scheduling data; simulate the goods multimodal transportation scheduling data to generate the goods multimodal transportation scheduling simulation data;

[0076] Step S4: Analyze the scheduling capacity of the goods multimodal transportation scheduling simulation data to generate the scheduling capacity analysis data; construct a joint scheduling plan for the goods multimodal transportation scheduling simulation data through the scheduling capacity analysis data to generate the joint scheduling plan data; perform a full-link transportation feedback on the logistics monitoring network according to the joint scheduling plan data and the logistics transportation abnormal detection data to generate the full-link transportation feedback data for executing the logistics goods transportation scheduling operation.

[0077] The present invention ensures the comprehensiveness and diversity of information by acquiring logistics node data and performing multi-dimensional data collection, enabling subsequent analysis to be based on a richer data foundation. Through the preprocessing of multi-dimensional logistics data, standard multi-dimensional logistics monitoring data is generated, which provides high-quality data support for the subsequent analysis and decision-making of the logistics system, reducing the decision-making risks caused by data inconsistency. By the distribution center node searching for the positions of adjacent logistics storage nodes, the rationality and effectiveness of path planning are ensured. Such operations not only improve transportation efficiency but also reduce transportation costs. Based on the retained data of warehouse scheduling, the initial path is screened to ensure the optimization of the transportation path, minimizing transportation time and resource consumption to the greatest extent. The goods transportation priorities of logistics order data are sorted, making resource allocation more reasonable, giving priority to meeting the transportation needs of high-priority orders, and enhancing customer satisfaction. Through the analysis of the sorted priority data, a normal goods transportation scheduling strategy is generated, further ensuring the efficiency and adaptability of transportation. Based on the anomaly detection of standard multi-dimensional logistics monitoring data, the system's ability to predict potential transportation delays is improved, identifying transportation problems in advance and helping managers adjust the scheduling plan in a timely manner to reduce the negative impact of delays. Through the multi-modal transport scheduling of goods transportation using the anomaly delay prediction data, the use of transportation resources is optimized, enabling flexible switching between transportation modes to adapt to different transportation needs. The generation and analysis of the multi-modal transport scheduling simulation data enable the prediction and adjustment of the effects of the scheduling plan before implementation, reducing the risks in actual operations. Through the analysis of the scheduling simulation data, the utilization rate of transportation resources can be evaluated and optimized in real time, ensuring the rationality of the transport capacity configuration and enhancing the efficiency of logistics operations. By combining the joint scheduling plan data with the logistics transportation anomaly detection data, full-link transportation feedback data is generated, making the information of each link in the logistics transportation transparent, facilitating managers to adjust strategies in a timely manner, and enhancing the overall logistics efficiency. This method provides effective data support for decision-makers by constructing a systematic logistics monitoring network and an intelligent data processing mechanism, making the decision-making process more scientific and accurate. In a constantly changing market environment, the scheduling method based on artificial intelligence can quickly adapt to new situations, ensuring the efficient operation of the logistics system and having strong adaptability. Therefore, the present invention improves the efficiency and reliability of logistics goods scheduling through multi-dimensional data collection, dynamic path optimization, delay prediction, and full-link feedback mechanism.

[0078] In an embodiment of the present invention, with reference to Figure 1 as described, it is a schematic diagram of the step flow of a method for scheduling logistics goods transportation based on artificial intelligence according to the present invention. In this example, the method for scheduling logistics goods transportation based on artificial intelligence includes the following steps:

[0079] Step S1: Obtain logistics node data; conduct multi-dimensional logistics data collection on the logistics node data to generate multi-dimensional logistics data; construct a logistics monitoring network based on the logistics node data as nodes and the multi-dimensional logistics data to generate a logistics monitoring network, where the logistics monitoring network includes warehousing nodes, distribution center nodes, and transportation tool nodes; perform data preprocessing on the multi-dimensional logistics data through the logistics monitoring network to generate standard multi-dimensional logistics monitoring data;

[0080] In the embodiments of the present invention, by identifying and determining the logistics nodes that need to be collected, including warehousing nodes, distribution center nodes, and transportation tool nodes. Using sensors (such as RFID tags, GPS devices) and data collection systems to collect the basic information (such as location, status, inventory level, etc.) of each logistics node in real time. Define the dimensions of multi-dimensional logistics data, such as time dimension, space dimension, quantity dimension, and status dimension. Integrate logistics information from different data sources to ensure data consistency and integrity. Adopt data cleaning and deduplication techniques to handle missing values and outliers. Convert the collected logistics data into a multi-dimensional data format to generate a multi-dimensional logistics data set. According to the logistics node data, take each logistics node as a node in the network and define the connection relationships between nodes (such as the relationship between warehousing and distribution centers). Design the structure of the logistics monitoring network, including the hierarchical relationships and interaction paths of each node, to ensure the smooth transmission of data streams. Use network construction tools (such as graph databases) to visualize the logistics monitoring network and assign unique identifiers to each node. Clean the multi-dimensional logistics data in the logistics monitoring network to eliminate redundant information and ensure data accuracy and consistency. Convert the multi-dimensional data into a preset standard format for subsequent analysis and processing. For example, convert quantities in different units into a unified standard unit. Finally, generate a standard multi-dimensional logistics monitoring data set, including cleaned and normalized data, to provide support for subsequent data analysis and decision-making.

[0081] Step S2: Search for the location of adjacent logistics warehousing nodes for the standard multi-dimensional logistics monitoring data through the distribution center node to generate adjacent warehousing node location information data; perform initial transportation path planning on the logistics cargo transportation destination data through the adjacent warehousing node location information data to generate initial logistics cargo transportation planning path data; conduct warehousing scheduling retention analysis on the standard multi-dimensional logistics monitoring data through the warehousing node to generate warehousing scheduling retention data; perform path screening on the initial logistics cargo transportation planning path data based on the warehousing scheduling retention data to generate optimized logistics cargo transportation planning path data;

[0082] In the embodiments of the present invention, by using standard multi-dimensional logistics monitoring data, the location information of warehousing nodes (such as longitude and latitude, address, etc.) is extracted. The warehousing nodes are searched for adjacent locations by the distribution center nodes, and the warehousing nodes adjacent to the distribution center are identified by using a Geographic Information System (GIS) or other spatial analysis tools, and a database containing the location information of the adjacent warehousing nodes is generated, and the relevant attributes of the adjacent nodes (such as distance, capacity, etc.) are recorded. According to the transportation destination of the logistics goods, the location information and relevant attributes of the destination (such as priority, timeliness, etc.) are extracted. By using a path planning algorithm (such as Dijkstra algorithm, etc.), combined with the location information data of the adjacent warehousing nodes, the initial transportation path of the logistics goods is planned, and the initial logistics goods transportation planning path data is generated, including information such as the warehousing nodes passed through, transportation time, transportation distance, etc. The standard multi-dimensional logistics monitoring data is analyzed, and information such as the inbound and outbound records, storage cycle, and goods turnover rate of the warehousing nodes is collected. Data analysis techniques (such as regression analysis, time series analysis) are applied to analyze the scheduling retention situation of the warehousing nodes, evaluate the efficiency and retention rate of warehousing scheduling, generate warehousing scheduling retention data, and record the retention situation and scheduling efficiency of each warehousing node for subsequent analysis. According to the warehousing scheduling retention data, path screening criteria are set, such as indicators of transportation timeliness, cost, risk, etc. By using an optimization algorithm (such as genetic algorithm, simulated annealing algorithm, etc.), the initial logistics goods transportation planning path data is screened and optimized, considering each screening criterion, and the optimized logistics goods transportation planning path data is generated to ensure the best performance of the final path in various indicators.

[0083] Step S3: According to the optimized path data of the logistics goods transportation plan, the goods transportation priorities of the logistics order data are sorted to generate goods transportation priority sorting data; according to the goods transportation priority sorting data, the transportation mode is confirmed to generate a normal goods transportation scheduling strategy; based on the transportation tool nodes, the standard multi-dimensional logistics monitoring data is used to predict abnormal delays in transportation to generate abnormal delay prediction data; through the abnormal delay prediction data, multi-modal transportation scheduling of the goods transportation is performed to generate goods transportation multi-modal transportation scheduling data; the goods transportation multi-modal transportation scheduling data is simulated to generate goods transportation multi-modal transportation scheduling simulation data;

[0084] In the embodiments of the present invention, relevant information of each logistics order is extracted from the optimized path data of logistics goods transportation planning, including the order quantity, delivery deadline, customer priority, etc. According to the importance of the order, delivery time limit, and customer requirements, a priority ranking standard for goods transportation is set. A sorting algorithm (such as the weighted scoring method) is applied to calculate each order, generate priority ranking data for goods transportation, and determine the transportation priority of each order. According to the priority ranking data of goods transportation, criteria for confirming the transportation mode are set, such as cost, timeliness, and goods characteristics (such as fragile, perishable). The suitability of different transportation modes (such as land transportation, sea transportation, air transportation) for each order is analyzed, and timeliness and cost-effectiveness are comprehensively considered. According to the evaluation results, a normal goods transportation scheduling strategy is generated, clarifying the transportation mode and related scheduling details of each order. Based on the transportation tool nodes, standard multi-dimensional logistics monitoring data is analyzed, and historical transportation data is collected, including transportation time, delay records, and abnormal events, etc. Time series analysis or machine learning models (such as regression analysis, LSTM network) are applied to predict transportation abnormal delays, generate abnormal delay prediction data, identify potential transportation delay risks, and evaluate the delay range. Using the abnormal delay prediction data, a comprehensive analysis of goods transportation scheduling is carried out to identify factors affecting transportation efficiency in multimodal transportation. A multimodal transportation scheduling plan for goods transportation is formulated, reasonably allocating different transportation tools (such as trucks, ships, airplanes) and routes to improve the overall transportation efficiency, generating multimodal transportation scheduling data for goods transportation, and detailing the execution plan of each transportation link. A transportation scheduling simulation environment is established, and virtual tests of transportation scheduling are carried out using computer simulation software (such as AnyLogic, MATLAB, etc.). The generated multimodal transportation scheduling data for goods transportation is executed in the simulation environment, observing the dynamic changes during the transportation process, evaluating the effectiveness of the scheduling strategy, generating multimodal transportation scheduling simulation data for goods transportation, and recording key indicators during the simulation process (such as transportation time, cost, delay situation, etc.) for reference in subsequent decision-making.

[0085] Step S4: Conduct scheduling capacity analysis on the multimodal transportation scheduling simulation data for goods transportation to generate scheduling capacity analysis data; construct a joint scheduling plan for the multimodal transportation scheduling simulation data for goods transportation through the scheduling capacity analysis data to generate joint scheduling plan data; perform full-link transportation feedback on the logistics monitoring network according to the joint scheduling plan data and logistics transportation anomaly detection data to generate full-link transportation feedback data for executing the logistics goods transportation scheduling operation.

[0086] In the embodiments of the present invention, relevant indicators are extracted from the multimodal transport scheduling simulation data of goods transportation, including information such as the load capacity, transportation time, and scheduling frequency of transportation tools. A scheduling capacity evaluation model is established, considering the capacity of each transportation tool, the timeliness of scheduling, and the matching degree between them and the goods demand. Analyze the capacity of the simulation data, evaluate the impact of different transportation modes and scheduling strategies on the overall capacity, identify situations of insufficient or redundant capacity, generate scheduling capacity analysis data, and provide a visual report on the capacity utilization efficiency for subsequent decision-making reference. According to the scheduling capacity analysis data, set the construction criteria for the joint scheduling plan to ensure the coordination and reasonable allocation of the capacity of each transportation tool. Use joint scheduling algorithms (such as linear programming, optimal scheduling algorithms, etc.), combined with the characteristics of transportation tools and scheduling requirements, to construct a joint scheduling plan. Verify the initially constructed joint scheduling plan to ensure that the plan is feasible in actual scheduling and can maximize the capacity utilization rate. Make adjustments if necessary to generate joint scheduling plan data, and record in detail the scheduling arrangements and plans of each transportation tool. Integrate the joint scheduling plan data with the logistics transportation anomaly detection data to analyze the transportation status and risks of each link. Use the logistics monitoring network to conduct full-link monitoring of each link of goods transportation to ensure the real-time update and feedback of information. According to the real-time monitoring results, establish a feedback mechanism to promptly feedback abnormal situations to the scheduling system, adjust the transportation strategy or scheduling plan, generate full-link transportation feedback data, and record the feedback information and corresponding adjustment measures to support subsequent logistics goods transportation scheduling operations.

[0087] Preferably, step S1 includes the following steps:

[0088] Step S11: Obtain logistics node data;

[0089] Step S12: Use edge computing network technology to deploy sensing devices for the logistics node data to obtain logistics node sensing device deployment data; collect multi-dimensional logistics data from the logistics node sensing device deployment data to generate multi-dimensional logistics data;

[0090] Step S13: Use the logistics node data as nodes and the multi-dimensional logistics data as edges to construct a logistics monitoring network, generating a logistics monitoring network, where the logistics monitoring network includes warehousing node, distribution center node, and transportation tool nodes;

[0091] Step S14: Perform data preprocessing on the multi-dimensional logistics data through the logistics monitoring network to generate standard multi-dimensional logistics monitoring data, where the data preprocessing includes data cleaning, data denoising, data normalization, and data standardization.

[0092] In the embodiments of the present invention, by obtaining logistics node data related to the logistics chain, these node data generally come from the following categories: Warehouse nodes: including warehouse locations, inventory information, warehousing equipment, etc. Distribution center nodes: including distribution center locations, scheduling information, goods sorting data, etc. Transportation tool nodes: including location information, status information, route planning, etc. of transportation tools such as trucks, airplanes, and ships. These node data can be collected through channels such as existing databases, RFID, GPS sensors, and inventory management systems in the logistics system. The collection of node data is the basis for system construction. Install sensors on warehouse nodes, distribution center nodes, and transportation tool nodes, covering environmental sensors (such as temperature, humidity), positioning sensors, goods status monitoring sensors, etc. These sensors perform real-time data collection through an edge computing network. The sensing devices collect various data in the logistics nodes to form multi-dimensional logistics data, which includes but is not limited to: location information (GPS), goods temperature and humidity information, the operating status of transportation tools (such as fuel consumption, speed, etc.), and the goods storage conditions of warehouse nodes (such as inventory quantity, goods arrangement, etc.). The edge computing network can quickly process this data between the sensors and the central server, and perform preliminary analysis and filtering, thus reducing the central processing pressure. Based on the logistics node data obtained in step S11 and the multi-dimensional logistics data collected in step S12, the system constructs a logistics monitoring network from the node data and multi-dimensional data: Warehouse nodes, distribution center nodes, and transportation tool nodes serve as vertices in the network, and these nodes are connected through the logistics data between each node. The edges represent information such as the goods circulation path, transportation time, and goods status between each node. After the logistics monitoring network is formed, it can comprehensively reflect the operation of the entire logistics chain and provide real-time monitoring between different nodes and paths. Preprocess the data within the logistics monitoring network to remove illogical data such as outliers and missing values in the data. For example, if there is a deviation in the GPS position of a certain node, the system will detect and eliminate this data. Denoise the sensing data through edge computing devices to remove influencing factors such as sensor errors and network transmission noise, and ensure the accuracy of the data. Normalize the data of different dimensions to unify the magnitude and range of the data, facilitating subsequent analysis. For example, normalize different types of data such as temperature, humidity, and location to the same scale. Use standardization rules to transform the data, so that data from different sources and different formats are presented under the same standard, thereby improving the comparability and processing efficiency of the data. Finally, after data cleaning, denoising, normalization, and standardization processing, standard multi-dimensional logistics monitoring data is generated, which not only ensures its accuracy but also provides strong support for subsequent logistics optimization and decision-making.

[0093] As an example of the present invention, refer to Figure 2 shown, in this example, step S2 includes:

[0094] Step S21: Extract logistics order from the standard multi-dimensional logistics monitoring data through the distribution center node to obtain logistics order data; perform destination analysis on the logistics order data to generate logistics cargo transportation destination data;

[0095] Step S22: Search for the positions of adjacent warehouse nodes for the logistics cargo transportation destination data to generate adjacent warehouse node position information data; perform initial transportation path planning on the logistics cargo transportation destination data through the adjacent warehouse node position information data to generate initial logistics cargo transportation planning path data;

[0096] Step S23: Extract warehouse storage space from the standard multi-dimensional logistics monitoring data through the warehouse node to obtain warehouse storage space data; perform available space analysis on the warehouse storage space data to generate available warehouse storage space data;

[0097] Step S24: Perform warehouse scheduling retention analysis on the available warehouse storage space data to generate warehouse scheduling retention data; perform path screening on the initial logistics cargo transportation planning path data based on the warehouse scheduling retention data to generate optimized logistics cargo transportation planning path data.

[0098] In the embodiments of the present invention, the distribution center node extracts order data from the standard multi-dimensional logistics monitoring data. Specifically, the distribution center node can screen out the current logistics orders to be processed according to the information such as the real-time monitored goods, vehicles, and warehousing status, and generate logistics order data. For example, when the goods arrive at the distribution center, the system will extract the relevant information of the goods according to the logistics order data, including the quantity of goods, transportation requirements, customer information, etc. After generating the logistics order data, the system analyzes the destinations in each order to identify the logistics goods transportation destination data of each order. This data reflects the final delivery location of each good and is used for subsequent transportation route planning. For example, if the destination of an order is Beijing, the system will generate relevant transportation destination data based on this information. According to the logistics goods transportation destination data generated in step S21, the system searches for the location information of adjacent warehousing nodes. This operation determines the warehousing node closest to the destination through the Geographic Information System (GIS) or the location data in the warehousing network, and generates the location information data of adjacent warehousing nodes. For example, for an order destined for Beijing, the system will search for the location information of the warehousing nodes around Beijing to find the best storage or transfer point for the goods. Using the location information data of adjacent warehousing nodes, the system makes an initial route plan for the logistics goods. The plan is based on the existing traffic routes, the layout of warehousing nodes, and the real-time traffic conditions, and generates the initial logistics goods transportation plan route data. For example, if a good is shipped from Shanghai to Beijing, the system will plan an initial transportation route and consider the warehousing nodes along the way as transfer or alternative routes. The system analyzes the standard multi-dimensional logistics monitoring data through the warehousing nodes to extract the warehousing storage space data of the current warehousing node. This data includes information such as the existing storage capacity, types of goods, and storage conditions in each warehousing node. For example, the system will analyze whether there is available storage space in a certain warehousing node to accept the upcoming goods. Based on the extracted warehousing storage space data, the system conducts an available space analysis to generate the available warehousing storage space data, which reflects the storage capacity that the warehousing node can currently allocate to new goods, ensuring that the goods can smoothly enter the appropriate warehouse in the logistics chain. For example, a certain warehousing node has 500 cubic meters of available space but requires special refrigeration conditions, and the system will analyze and generate specific available space data accordingly. The system further analyzes the available warehousing storage space data to evaluate whether the warehousing node needs to reserve storage space for future orders or existing goods, and generates the warehousing scheduling retention data. This step helps the system ensure that the warehousing node will not be overloaded and that logistics will not be stagnated due to insufficient space. For example, a certain warehousing node needs to reserve space for a large number of upcoming goods, so the system will make a space reservation decision based on future logistics requirements. Finally, based on the generated warehousing scheduling retention data, the system screens and optimizes the previous initial logistics goods transportation plan route data.By excluding the paths with insufficient storage node space or tight scheduling, the system can generate more efficient optimized path data for the transportation planning of logistics goods. For example, if a certain storage node passed by the initial planned path has insufficient space, the system will re-plan the path to transport the goods to another storage node to ensure smooth transportation and reasonable utilization of storage.

[0099] Preferably, step S24 includes the following steps:

[0100] Step S241: Conduct a temporal trend analysis of the available storage space data to generate temporal trend data of available space; convert the temporal trend data of available space into a curve to generate a temporal trend curve of available space;

[0101] Step S242: Calculate the curve curvature of the temporal trend curve of available space to obtain the curvature data of available storage space; determine the positive and negative values of the curvature data of available storage space. When the curvature data of available storage space is positive, mark the corresponding storage node as in a crowded state based on the curvature data of available storage space to generate crowded storage node data;

[0102] Step S243: When the curvature data of available storage space is negative, mark the corresponding storage node as in an idle state based on the curvature data of available storage space to generate idle storage node data; conduct the first path screening on the initial logistics goods transportation planning path data according to the crowded storage node data and the idle storage node data, and eliminate the crowded storage node data, thereby generating a screened path for the logistics goods transportation planning;

[0103] Step S244: Conduct a storage scheduling retention analysis on the available storage space data according to the idle storage node data to generate storage scheduling retention data; conduct path screening on the initial logistics goods transportation planning path data based on the storage scheduling retention data to generate optimized path data for the logistics goods transportation planning.

[0104] In the embodiments of the present invention, by performing time series analysis on the available data of the storage space in the warehouse, the available space conditions of each warehouse node at different times are obtained. This analysis helps to understand the usage trend, change pattern, and future available space prediction of the warehouse space, generating time series trend data of available space, which includes the usage conditions of the warehouse space at each time point. The time series trend data of available space is converted into a curve form to generate a time series trend curve of available space. This curve can intuitively reflect the usage trend of the warehouse space, facilitating subsequent analysis. Methods such as interpolation method and spline curve can be used for curve conversion to smooth data fluctuations. The curvature of the generated time series trend curve of available space is calculated to obtain the available curvature data of the warehouse space. The curvature reflects the speed of curve change and can indicate the change trend of the available space state. The relationship between the first derivative and the second derivative is used for curvature calculation, and the formula is as follows: Curvature = (1 + (y')^2)^(3 / 2) / y'', where y' and y'' are the first and second derivatives of the curve respectively. The positive and negative values of the available curvature data of the warehouse space are discriminated. When the curvature data is positive, it indicates that the space availability is increasing, meaning the warehouse node is gradually becoming crowded. Based on this judgment, the corresponding warehouse node is marked as crowded, generating crowded warehouse node data. When the available curvature data of the warehouse space is negative, it indicates that the space availability is decreasing, meaning the warehouse node is relatively idle. In this regard, the system marks the corresponding warehouse node as idle, generating idle warehouse node data. According to the generated crowded warehouse node data and idle warehouse node data, the initial logistics goods transportation planning path data is screened for the first time. The crowded warehouse nodes passed through in the path are removed, generating the screened path of the logistics goods transportation planning. This screening ensures that the goods can avoid crowded warehouse nodes as much as possible during transportation, reducing the risk of delays. The available data of the warehouse storage space is deeply analyzed using the idle warehouse node data to generate warehouse scheduling retention data. This data indicates the amount of space that can be retained by the idle warehouse node in a future period of time and the demand for retaining new arriving goods. For example, if a certain idle warehouse node has goods arriving in the future prediction, a certain amount of space needs to be retained to cope with the arrival of new goods. Based on the generated warehouse scheduling retention data, the previous initial logistics goods transportation planning path data is further screened to ensure that each transportation path passes through warehouse nodes with sufficient storage space. Finally, the optimized path data of the logistics goods transportation planning is generated, which will maximize the transportation efficiency and ensure the smoothness and timeliness of the goods during transportation.

[0105] As an example of the present invention, referring to Figure 3 shown, in this example, step S3 includes:

[0106] Step S31: Extract the logistics cargo characteristics from the logistics order data to obtain logistics cargo characteristic data; evaluate the importance of the cargo based on the logistics cargo characteristic data to generate cargo importance evaluation data; sort the logistics order data according to the optimized path data of the logistics cargo transportation based on the cargo importance evaluation data to generate cargo transportation priority ranking data;

[0107] Step S32: Confirm the transportation mode according to the cargo transportation priority ranking data to generate a normal cargo transportation scheduling strategy; extract transportation data from the standard multi-dimensional logistics monitoring data through the normal cargo transportation scheduling strategy based on the transportation tool nodes to obtain logistics transportation data;

[0108] Step S33: Detect transportation anomalies in the logistics transportation data to generate logistics transportation anomaly detection data; predict abnormal delays for the logistics order data based on the logistics transportation anomaly detection data to generate abnormal delay prediction data;

[0109] Step S34: Conduct multi-modal transportation scheduling for the logistics transportation data through the abnormal delay prediction data to generate cargo transportation multi-modal transportation scheduling data; simulate the scheduling for the cargo transportation multi-modal transportation scheduling data to generate cargo transportation multi-modal transportation scheduling simulation data.

[0110] In the embodiments of the present invention, by extracting features from logistics order data and analyzing the attributes of each cargo (such as weight, volume, vulnerability, shelf life, etc.) to generate logistics cargo feature data, which can be achieved through data mining and machine learning technologies, features related to transportation efficiency and risks are extracted. Based on the extracted logistics cargo feature data, an assessment of the importance of the cargo is carried out. Using a weight algorithm, factors such as the value of the cargo, urgency, and customer needs are considered to generate cargo importance assessment data. According to the cargo importance assessment data, the transportation priorities of logistics orders are sorted to generate cargo transportation priority sorting data. Cargo with a high priority should be arranged for transportation first to improve the overall transportation efficiency and customer satisfaction. According to the cargo transportation priority sorting data, a suitable transportation mode (such as land transportation, sea transportation, air transportation, etc.) is confirmed to generate a normal cargo transportation scheduling strategy. This strategy should consider factors such as the characteristics of the cargo, transportation time, and cost. Based on the transportation tool nodes, the standard multi-dimensional logistics monitoring data is analyzed using the normal cargo transportation scheduling strategy to extract relevant logistics transportation data, including transportation time, route, transportation tool status, etc. The extracted logistics transportation data is analyzed to identify potential transportation anomalies (such as delays, damages, losses, etc.) to generate logistics transportation anomaly detection data. Anomaly detection algorithms (such as Isolation Forest, Support Vector Machine, etc.) can be used for model training and identification. Based on the generated logistics transportation anomaly detection data, an abnormal delay prediction for the logistics order is carried out to generate abnormal delay prediction data. This prediction can use methods such as time series analysis and regression models to predict the possible delay time and its reasons. Using the abnormal delay prediction data, a multimodal transportation scheduling for the logistics transportation data is carried out to generate cargo transportation multimodal scheduling data. This scheduling should consider the advantages and disadvantages of different transportation modes and how to efficiently switch between different transportation modes. A scheduling simulation is carried out on the generated cargo transportation multimodal scheduling data to generate cargo transportation multimodal scheduling simulation data. The scheduling results can be evaluated through a simulation model to analyze the transportation time, cost, and efficiency in different situations for optimization and adjustment.

[0111] Preferably, step S33 includes the following steps:

[0112] Step S331: Confirm the transportation position coordinates of the logistics transportation data to obtain the logistics transportation position coordinates; update the coordinates of the logistics transportation position coordinates based on a preset time interval to generate updated logistics transportation position coordinates;

[0113] Step S332: Construct a coordinate movement trajectory for the logistics transportation position coordinates and the updated logistics transportation position coordinates to generate coordinate update trajectory data; discretize the coordinate update trajectory data to generate coordinate update trajectory discrete points; calculate the distances between adjacent discrete points of the coordinate update trajectory discrete points to obtain coordinate update discrete point distance data;

[0114] Step S333: Compare the discrete point distance data updated according to the coordinates with a preset discrete point distance threshold. When the discrete point distance data updated by the coordinates is less than the preset discrete point distance threshold, mark the corresponding coordinate update trajectory data as abnormal coordinate trajectory data;

[0115] Step S334: Perform transportation anomaly detection on the logistics transportation data based on the abnormal coordinate trajectory data to generate logistics transportation anomaly detection data; partition the logistics transportation anomaly detection data into a dataset to generate a model training set and a model test set; train the model training set through a long short-term memory network algorithm to generate an abnormal delay prediction pre-model;

[0116] Step S335: Optimize and iterate the abnormal delay prediction pre-model through the model test set to generate an abnormal delay prediction model; import the logistics transportation anomaly detection data and logistics order data into the abnormal delay prediction model for abnormal delay prediction to generate abnormal delay prediction data.

[0117] In the embodiments of the present invention, for logistics transportation data, the location information of each transportation node is extracted to determine the logistics transportation location coordinates. The location coordinates are usually obtained by GPS devices to ensure the accuracy of the location. Based on a preset time interval (such as every 5 minutes, 10 minutes, etc.), the obtained logistics transportation location coordinates are updated regularly to generate updated logistics transportation location coordinates. This process can be achieved through scheduled tasks or real-time data stream processing. Using the current logistics transportation location coordinates and the updated logistics transportation location coordinates, the coordinate movement trajectory of the transportation path is constructed to generate coordinate update trajectory data. This trajectory represents the location changes at each time point during the transportation process. The coordinate update trajectory data is discretized to generate coordinate update trajectory discrete points. This step can sample the trajectory points at a certain interval. The distances between the coordinate update trajectory discrete points are calculated to generate coordinate update discrete point distance data. This step can be achieved through the Euclidean distance formula or other suitable distance calculation methods. According to the comparison between the coordinate update discrete point distance data and the preset discrete point distance threshold, if the distance data is less than the preset threshold, it is determined as an abnormal situation. The coordinate update trajectory data that meets the abnormal criteria is marked as abnormal coordinate trajectory data for subsequent analysis and processing. Based on the marked abnormal coordinate trajectory data, the logistics transportation data is comprehensively analyzed to generate logistics transportation anomaly detection data. This process can be combined with machine learning algorithms to improve the detection accuracy. The generated logistics transportation anomaly detection data is divided into a model training set and a model test set, generally 70% for training and 30% for testing. The long short-term memory network (LSTM) algorithm is used to train the model training set to generate an abnormal delay prediction pre-model. This model can capture the long-term dependencies in time series data. The generated abnormal delay prediction pre-model is optimized and iterated through the model test set, the model performance is evaluated, and the model parameters are adjusted according to the test results to finally generate an abnormal delay prediction model. The logistics transportation anomaly detection data and the logistics order data are imported into the abnormal delay prediction model for actual abnormal delay prediction to generate the final abnormal delay prediction data.

[0118] Preferably, step S34 includes the following steps:

[0119] Step S341: Conduct an initial transportation mode analysis on the logistics transportation data to generate initial transportation mode data; segment the delay sections of the logistics transportation data through the abnormal delay prediction data to generate delay section segmentation data;

[0120] Step S342: Conduct an intermodal mode matching analysis on the delay section segmentation data to generate multimodal transportation feasibility data, where the intermodal modes include land transportation, sea transportation, air transportation, and rail transportation; allocate transportation resources to the delay section segmentation data according to the multimodal transportation feasibility data to generate goods transportation multimodal transportation scheduling data;

[0121] Step S343: Reconstruct the path of the delay section segmentation data according to the multimodal transport scheduling data of goods transportation to generate multimodal transport reconstructed path data;

[0122] Step S344: Conduct scheduling simulation on the delay section segmentation data through the multimodal transport reconstructed path data to generate goods transportation multimodal transport scheduling simulation data.

[0123] In the embodiment of the present invention, by comprehensively analyzing the logistics transportation data, the mode used for the current goods transportation (such as land transportation, sea transportation, air transportation, railway transportation, etc.) is identified to generate initial transportation mode data. This analysis can be comprehensively evaluated using factors such as historical data, transportation time, and cost. Using the abnormal delay prediction data, the logistics transportation data is divided into delay sections to identify the transportation sections with delay risks and generate delay section segmentation data, which can mark the sections that exceed the normal transportation time by setting thresholds. For the delay section segmentation data, multimodal transport mode matching analysis is carried out to generate multimodal transport feasibility data. This step needs to evaluate the applicability of different transportation modes on specific sections, including the feasibility of land transportation, sea transportation, air transportation, and railway transportation, considering time, cost, and cargo characteristics. According to the generated multimodal transport feasibility data, resource optimization allocation is carried out on the delay section segmentation data to ensure the selection of appropriate transportation modes and resources to generate goods transportation multimodal transport scheduling data. This process needs to comprehensively consider the availability and timeliness of transportation tools. Using the generated goods transportation multimodal transport scheduling data, the delay section segmentation data is re-planned and reconstructed to generate multimodal transport reconstructed path data. This step can combine route optimization algorithms to ensure the optimal transportation path while reducing delays. Based on the multimodal transport reconstructed path data, scheduling simulation is carried out on the delay section segmentation data to generate goods transportation multimodal transport scheduling simulation data. This step can use a simulation model to test the new transportation scheduling strategy and analyze its effects and efficiency in actual operation.

[0124] Preferably, step S4 includes the following steps:

[0125] Step S41: Extract the scheduling delivery time from the goods transportation multimodal transport scheduling simulation data to generate scheduling delivery time data; conduct scheduling capacity analysis on the scheduling delivery time data and the abnormal delay prediction data to generate scheduling capacity analysis data;

[0126] Step S42: Construct a joint scheduling plan for the goods transportation multimodal transport scheduling simulation data through the scheduling capacity analysis data to generate joint scheduling plan data;

[0127] Step S43: Match the combined scheduling plan data with the logistics transportation anomaly detection data to generate an abnormal transportation combined scheduling strategy; based on the normal cargo transportation scheduling strategy and the abnormal transportation combined scheduling strategy, perform full-link transportation feedback on the logistics monitoring network to generate full-link transportation feedback data for executing the logistics cargo transportation scheduling operation.

[0128] In the embodiment of the present invention, by extracting key scheduling delivery time information from the multi-modal transport scheduling simulation data of cargo transportation, including the estimated arrival time, the start and end times of transportation, etc., scheduling delivery time data is generated. This step can analyze historical transportation records through data mining technology to improve the accuracy of delivery time. Perform capacity analysis on the extracted scheduling delivery time data and abnormal delay prediction data to evaluate whether the capacity of each scheduling plan meets the expected demand. By combining factors such as the load capacity, availability, and estimated transportation time of transportation tools, scheduling capacity analysis data is generated, which will help identify potential capacity shortages or surpluses. According to the generated scheduling capacity analysis data, comprehensively analyze the multi-modal transport scheduling simulation data of cargo transportation to construct combined scheduling plan data. In this step, the scheduling of each transportation mode is integrated to ensure the effective scheduling and delivery of goods in the shortest time. Match the generated combined scheduling plan data with the logistics transportation anomaly detection data to identify the best scheduling strategy in abnormal transportation situations and generate an abnormal transportation combined scheduling strategy. This step ensures that transportation challenges can be effectively addressed in abnormal situations by comparing scheduling plans in normal and abnormal situations. Based on the normal cargo transportation scheduling strategy and the abnormal transportation combined scheduling strategy, perform full-link transportation feedback on the logistics monitoring network, which includes real-time updating of transportation status, tracking of cargo locations, and adjustment of transportation plans. Finally, full-link transportation feedback data is generated to ensure the efficient execution of the logistics cargo transportation scheduling operation. The feedback data can be used to optimize future scheduling plans and further improve the overall transportation efficiency.

[0129] In this specification, a logistics cargo transportation scheduling system based on artificial intelligence is provided for executing the above-mentioned logistics cargo transportation scheduling method based on artificial intelligence. The logistics cargo transportation scheduling system based on artificial intelligence includes:

[0130] A logistics network construction module, configured to obtain logistics node data; perform multi-dimensional logistics data collection on the logistics node data to generate multi-dimensional logistics data; construct a logistics monitoring network based on the logistics node data as nodes and the multi-dimensional logistics data to generate a logistics monitoring network, where the logistics monitoring network includes warehousing node, distribution center nodes, and transportation tool nodes; perform data preprocessing on the multi-dimensional logistics data through the logistics monitoring network to generate standard multi-dimensional logistics monitoring data;

[0131] The path planning module is used to search for the locations of adjacent logistics storage nodes in the standard multi-dimensional logistics monitoring data through the distribution center node, and generate the location information data of adjacent storage nodes; plan the initial transportation path for the logistics cargo transportation destination data through the location information data of adjacent storage nodes, and generate the initial logistics cargo transportation planning path data; analyze the warehousing scheduling retention of the standard multi-dimensional logistics monitoring data through the storage node, and generate the warehousing scheduling retention data; screen the initial logistics cargo transportation planning path data based on the warehousing scheduling retention data, and generate the optimized path data for logistics cargo transportation planning.

[0132] The transportation scheduling module is used to sort the priorities of cargo transportation for the logistics order data according to the optimized path data for logistics cargo transportation planning, and generate the cargo transportation priority sorting data; confirm the transportation mode according to the cargo transportation priority sorting data, and generate the normal cargo transportation scheduling strategy; predict the abnormal delay of transportation based on the standard multi-dimensional logistics monitoring data through the transportation tool node, and generate the abnormal delay prediction data; perform the multi-modal transportation scheduling of cargo transportation through the abnormal delay prediction data, and generate the multi-modal transportation scheduling data of cargo transportation; simulate the multi-modal transportation scheduling of cargo transportation for the multi-modal transportation scheduling data of cargo transportation, and generate the simulation data of multi-modal transportation scheduling of cargo transportation.

[0133] The link feedback module is used to analyze the scheduling capacity of the multi-modal transportation scheduling simulation data of cargo transportation, and generate the scheduling capacity analysis data; construct the joint scheduling plan for the multi-modal transportation scheduling simulation data of cargo transportation through the scheduling capacity analysis data, and generate the joint scheduling plan data; perform the full-link transportation feedback on the logistics monitoring network according to the joint scheduling plan data and the logistics transportation abnormal detection data, and generate the full-link transportation feedback data to execute the logistics cargo transportation scheduling operation.

[0134] The beneficial effects of the present invention are as follows. By comprehensively acquiring logistics node data, it can ensure that the system has a rich information basis, which helps with subsequent analysis and decision-making, generates multi-dimensional logistics data, and constructs a monitoring network to achieve real-time monitoring of warehouses, distribution centers, and transportation tools, thereby enhancing logistics transparency. Standardize multi-dimensional logistics monitoring data to make it suitable for subsequent analysis, ensuring data quality and consistency, and thus improving the accuracy of decision-making. Through adjacent node search, the system can quickly identify the best warehouse location, provide a basis for route planning, reduce transportation time and costs, and the generated initial transportation planning route provides a reasonable transportation plan for logistics goods to ensure the timely delivery of goods. By analyzing warehouse scheduling data, potential scheduling problems can be identified, which helps optimize inventory management and resource allocation. Based on the scheduling retention data, route optimization is carried out to ensure the selection of the best transportation route, improve transportation efficiency and customer satisfaction. Prioritize transportation orders so that important orders can be processed in a timely manner and resource utilization is optimized. The normal goods transportation scheduling strategy formulated based on priority ensures transportation in the most appropriate way and improves the response speed. Predict the risk of transportation delays, take countermeasures in advance, and reduce losses caused by delays. Improve transportation flexibility and efficiency through multimodal transportation scheduling, making the connection between different transportation modes smoother. Simulating the scheduling can evaluate the feasibility of different solutions, optimize actual scheduling decisions, and reduce risks. Analyzing the scheduling capacity can identify potential bottlenecks and resource waste, thereby achieving more efficient resource allocation. Generate a combined scheduling plan based on capacity analysis, enabling multiple transportation links to work in coordination and enhancing the overall efficiency. Through full-link transportation feedback, the logistics process can be monitored in real time, strategies can be adjusted in a timely manner, ensuring the smoothness and efficiency of logistics operations, and enhancing the adaptability and response speed of the overall supply chain. Therefore, the present invention improves the efficiency and reliability of logistics goods scheduling through multi-dimensional data collection, dynamic route optimization, delay prediction, and full-link feedback mechanisms.

[0135] Therefore, from any perspective, the embodiments should be regarded as exemplary and non-limiting. The scope of the present invention is defined by the appended claims rather than the above description. Therefore, it is intended to cover all changes falling within the meaning and scope of the equivalent elements of the application documents within the present invention.

[0136] The above are only specific embodiments of the present invention, enabling those skilled in the art to understand or implement the present invention. Various modifications to these embodiments will be obvious to those skilled in the art. The general principles defined herein can be implemented in other embodiments without departing from the spirit or scope of the present invention. Therefore, the present invention will not be limited to these embodiments shown herein, but will conform to the widest scope consistent with the principles and novel features invented herein.

Claims

1. A logistics cargo transportation scheduling method based on artificial intelligence, characterized in that, Including the following steps: Step S1: Obtain logistics node data; Perform multi-dimensional logistics data collection on the logistics node data to generate multi-dimensional logistics data; Construct a logistics monitoring network based on the logistics node data as nodes and the multi-dimensional logistics data, generating a logistics monitoring network, where the logistics monitoring network includes warehousing nodes, distribution center nodes, and transportation tool nodes; perform data preprocessing on the multi-dimensional logistics data through the logistics monitoring network to generate standard multi-dimensional logistics monitoring data; Step S2: Search for the positions of adjacent logistics warehousing nodes in the standard multi-dimensional logistics monitoring data through the distribution center nodes to generate adjacent warehousing node position information data; perform initial transportation path planning on the logistics cargo transportation destination data through the adjacent warehousing node position information data to generate initial logistics cargo transportation planning path data; perform warehousing scheduling retention analysis on the standard multi-dimensional logistics monitoring data through the warehousing nodes to generate warehousing scheduling retention data; Based on the warehousing scheduling retention data, screen the initial logistics cargo transportation planning path data to generate optimized logistics cargo transportation planning path data; Step S3: Sort the goods transportation priorities of the logistics order data according to the optimized logistics cargo transportation planning path data to generate goods transportation priority sorting data; confirm the transportation mode according to the goods transportation priority sorting data to generate a normal goods transportation scheduling strategy; predict the abnormal delay of transportation based on the standard multi-dimensional logistics monitoring data through the transportation tool nodes to generate abnormal delay prediction data; perform multi-modal transportation scheduling of goods through the abnormal delay prediction data to generate multi-modal transportation scheduling data of goods; perform scheduling simulation on the multi-modal transportation scheduling data of goods to generate multi-modal transportation scheduling simulation data of goods; Step S4: Analyze the scheduling transportation capacity of the multi-modal transportation scheduling simulation data of goods to generate scheduling transportation capacity analysis data; construct a joint scheduling plan for the multi-modal transportation scheduling simulation data of goods through the scheduling transportation capacity analysis data to generate joint scheduling plan data; perform full-link transportation feedback on the logistics monitoring network according to the joint scheduling plan data and the logistics transportation anomaly detection data to generate full-link transportation feedback data to execute the logistics cargo transportation scheduling operation.

2. The method for scheduling logistics cargo transportation based on artificial intelligence according to claim 1, wherein Step S1 includes the following steps: Step S11: Obtain logistics node data; Step S12: Use edge computing network technology to deploy sensing devices for the logistics node data to obtain logistics node sensing device deployment data; perform multi-dimensional logistics data collection on the logistics node sensing device deployment data to generate multi-dimensional logistics data; Step S13: Construct a logistics monitoring network with the logistics node data as nodes and the multi-dimensional logistics data as edges, generating a logistics monitoring network, where the logistics monitoring network includes warehousing nodes, distribution center nodes, and transportation tool nodes; Step S14: Perform data preprocessing on the multi-dimensional logistics data through the logistics monitoring network to generate standard multi-dimensional logistics monitoring data, where the data preprocessing includes data cleaning, data denoising, data normalization, and data standardization.

3. The method for scheduling logistics cargo transportation based on artificial intelligence according to claim 1, wherein, Step S2 includes the following steps: Step S21: Extract logistics orders from the standard multi-dimensional logistics monitoring data through the distribution center node to obtain logistics order data; perform destination analysis on the logistics order data to generate logistics goods transportation destination data; Step S22: Search for the positions of adjacent warehousing nodes based on the logistics goods transportation destination data to generate adjacent warehousing node position information data; perform initial transportation path planning on the logistics goods transportation destination data through the adjacent warehousing node position information data to generate initial logistics goods transportation planning path data; Step S23: Extract warehousing storage space from the standard multi-dimensional logistics monitoring data through the warehousing node to obtain warehousing storage space data; perform available space analysis on the warehousing storage space data to generate available warehousing storage space data; Step S24: Perform warehousing scheduling retention analysis on the available warehousing storage space data to generate warehousing scheduling retention data; based on the warehousing scheduling retention data, perform path screening on the initial logistics goods transportation planning path data to generate optimized logistics goods transportation planning path data.

4. The method for scheduling logistics cargo transportation based on artificial intelligence according to claim 3, wherein Step S24 includes the following steps: Step S241: Perform temporal trend analysis of available space on the available warehousing storage space data to generate temporal trend data of available space; convert the temporal trend data of available space into a curve to generate a temporal trend curve of available space; Step S242: Calculate the curve curvature of the temporal trend curve of available space to obtain available curvature data of the warehousing space; perform positive and negative value discrimination on the available curvature data of the warehousing space. When the available curvature data of the warehousing space is positive, mark the corresponding warehousing node as a congested state based on the available curvature data of the warehousing space to generate congested warehousing node data; Step S243: When the available curvature data of the warehousing space is negative, mark the corresponding warehousing node as an idle state based on the available curvature data of the warehousing space to generate idle warehousing node data; perform the first path screening on the initial logistics goods transportation planning path data according to the congested warehousing node data and the idle warehousing node data, and eliminate the congested warehousing node data to generate a screened path for logistics goods transportation planning; Step S244: Perform warehousing scheduling retention analysis on the available warehousing storage space data according to the idle warehousing node data to generate warehousing scheduling retention data; based on the warehousing scheduling retention data, perform path screening on the initial logistics goods transportation planning path data to generate optimized logistics goods transportation planning path data.

5. The method for scheduling logistics cargo transportation based on artificial intelligence according to claim 1, wherein Step S3 includes the following steps: Step S31: Extract logistics goods characteristics from the logistics order data to obtain logistics goods characteristic data; perform goods importance assessment on the logistics goods characteristic data to generate goods importance assessment data; based on the goods importance assessment data, sort the logistics order data according to the optimized logistics goods transportation planning path data to generate goods transportation priority sorting data; Step S32: Confirm the transportation mode according to the goods transportation priority sorting data to generate a normal goods transportation scheduling strategy; based on the transportation tool node, extract transportation data from the standard multi-dimensional logistics monitoring data through the normal goods transportation scheduling strategy to obtain logistics transportation data; Step S33: Perform transportation anomaly detection on the logistics transportation data to generate logistics transportation anomaly detection data; based on the logistics transportation anomaly detection data, perform anomaly delay prediction on the logistics order data to generate anomaly delay prediction data; Step S34: Use the anomaly delay prediction data to perform multimodal transport scheduling on the logistics transportation data to generate multimodal transport scheduling data for goods transportation; perform scheduling simulation on the multimodal transport scheduling data for goods transportation to generate multimodal transport scheduling simulation data for goods transportation.

6. The method for scheduling logistics cargo transportation based on artificial intelligence according to claim 5, wherein Step S33 includes the following steps: Step S331: Confirm the transportation location coordinates of the logistics transportation data to obtain the logistics transportation location coordinates; update the coordinates of the logistics transportation location coordinates based on a preset time interval to generate the updated logistics transportation location coordinates; Step S332: Construct a coordinate movement trajectory for the logistics transportation location coordinates and the updated logistics transportation location coordinates to generate coordinate update trajectory data; discretize the coordinate update trajectory data to generate coordinate update trajectory discrete points; calculate the distances between adjacent discrete points of the coordinate update trajectory discrete points to obtain coordinate update discrete point distance data; Step S333: Compare the coordinate update discrete point distance data with a preset discrete point distance threshold. When the coordinate update discrete point distance data is less than the preset discrete point distance threshold, mark the corresponding coordinate update trajectory data as abnormal coordinate trajectory data; Step S334: Perform transportation anomaly detection on the logistics transportation data based on the abnormal coordinate trajectory data to generate logistics transportation anomaly detection data; divide the logistics transportation anomaly detection data into a dataset to generate a model training set and a model test set; train the model training set through a long short-term memory network algorithm to generate an anomaly delay prediction pre-model; Step S335: Optimize and iterate the anomaly delay prediction pre-model through the model test set to generate an anomaly delay prediction model; import the logistics transportation anomaly detection data and the logistics order data into the anomaly delay prediction model to perform anomaly delay prediction and generate anomaly delay prediction data.

7. The method for scheduling logistics goods transportation based on artificial intelligence according to claim 6, characterized in that, Step S34 includes the following steps: Step S341: Analyze the initial transportation mode of the logistics transportation data to generate initial transportation mode data; divide the delayed sections of the logistics transportation data through the anomaly delay prediction data to generate delayed section division data; Step S342: Perform multimodal transport mode matching analysis on the delayed section division data to generate multimodal transport feasibility data, where the multimodal transport modes include land transport, sea transport, air transport, and rail transport; allocate transportation resources to the delayed section division data according to the multimodal transport feasibility data to generate multimodal transport scheduling data for goods transportation; Step S343: Reconstruct the path of the delayed section division data according to the multimodal transport scheduling data for goods transportation to generate multimodal transport reconstructed path data; Step S344: Perform scheduling simulation on the delayed section division data through the multimodal transport reconstructed path data to generate multimodal transport scheduling simulation data for goods transportation.

8. The method for scheduling logistics cargo transportation based on artificial intelligence according to claim 7, wherein, Step S4 includes the following steps: Step S41: Extract the scheduling delivery time from the simulation data of multimodal transport scheduling for goods transportation to generate scheduling delivery time data; perform scheduling capacity analysis on the scheduling delivery time data and abnormal delay prediction data to generate scheduling capacity analysis data; Step S42: Construct a joint scheduling plan for the simulation data of multimodal transport scheduling for goods transportation through the scheduling capacity analysis data to generate joint scheduling plan data; Step S43: Match the joint scheduling plan data with the abnormal detection data of logistics transportation to generate an abnormal transportation joint scheduling strategy; perform full-link transportation feedback on the logistics monitoring network according to the normal goods transportation scheduling strategy and the abnormal transportation joint scheduling strategy to generate full-link transportation feedback data, so as to execute the logistics goods transportation scheduling operation.

9. The method for scheduling logistics cargo transportation based on artificial intelligence according to claim 8, wherein, Step S41 includes the following steps: Step S411: Extract time nodes from the simulation data of multimodal transport scheduling for goods transportation to generate scheduling time node data; calculate the delivery time for the scheduling time node data to generate scheduling delivery time data; Step S412: Compare the scheduling delivery time data with the abnormal delay prediction data to generate time difference analysis data; perform capacity scheduling analysis on the time difference analysis data to generate preliminary scheduling capacity analysis data, where the capacity scheduling analysis formula is as follows: Wherein, U represents the capacity utilization rate, D represents the transportation demand, C represents the available capacity, E represents the scheduling efficiency factor, and T d represents the actual delay time, and T s represents the scheduled delivery time; Step S413: Optimize the capacity of the preliminary scheduling capacity analysis data to generate optimized scheduling capacity data; perform clustering analysis on the actual transportation situation of the optimized scheduling capacity data to generate scheduling capacity analysis data.

10. A logistics cargo transportation scheduling system based on artificial intelligence, characterized in that, For implementing the logistics goods transportation scheduling method based on artificial intelligence as described in claim 1, the logistics goods transportation scheduling system based on artificial intelligence includes: A logistics network construction module, configured to obtain logistics node data; collect multi-dimensional logistics data for the logistics node data to generate multi-dimensional logistics data; construct a logistics monitoring network based on the logistics node data as nodes and the multi-dimensional logistics data to generate a logistics monitoring network, where the logistics monitoring network includes warehousing node, distribution center node and transportation tool node; perform data preprocessing on the multi-dimensional logistics data through the logistics monitoring network to generate standard multi-dimensional logistics monitoring data; A path planning module, configured to search for the positions of adjacent logistics warehousing nodes for the standard multi-dimensional logistics monitoring data through the distribution center node to generate adjacent warehousing node position information data; perform initial transportation path planning on the logistics goods transportation destination data through the adjacent warehousing node position information data to generate initial logistics goods transportation planned path data; perform warehousing scheduling retention analysis on the standard multi-dimensional logistics monitoring data through the warehousing node to generate warehousing scheduling retention data; screen the initial logistics goods transportation planned path data based on the warehousing scheduling retention data to generate optimized logistics goods transportation planned path data; A transportation scheduling module, which is used to prioritize the goods transportation of logistics order data according to the optimized path data of the logistics goods transportation plan, and generate goods transportation priority ranking data; confirm the transportation mode according to the goods transportation priority ranking data, and generate a normal goods transportation scheduling strategy; predict the abnormal delay of the standard multi-dimensional logistics monitoring data based on the transportation tool nodes, and generate abnormal delay prediction data; perform multimodal transportation scheduling of goods transportation through the abnormal delay prediction data, and generate goods transportation multimodal transportation scheduling data; simulate the scheduling of the goods transportation multimodal transportation scheduling data, and generate goods transportation multimodal transportation scheduling simulation data; A link feedback module, which is used to analyze the scheduling capacity of the goods transportation multimodal transportation scheduling simulation data, and generate scheduling capacity analysis data; construct a joint scheduling plan for the goods transportation multimodal transportation scheduling simulation data through the scheduling capacity analysis data, and generate joint scheduling plan data; perform full-link transportation feedback on the logistics monitoring network according to the joint scheduling plan data and the logistics transportation abnormal detection data, and generate full-link transportation feedback data to execute the logistics goods transportation scheduling operation.

Images