An intelligent scheduling method and system based on artificial intelligence large model

Abstract

The present invention relates to the technical field of scheduling management, and specifically discloses an intelligent scheduling method and system based on an artificial intelligence big model. The method includes: generating a transportation scheduling route scheduling strategy for the current transportation tool based on current transportation tool sensor data, transportation space environment data, transportation scheduling route information, cargo information, same-space transportation tool collaboration information and an artificial intelligence big model; generating a terminal freight hub scheduling strategy for the current transportation tool based on current cargo information, freight hub information, same-space transportation tool collaboration information and an artificial intelligence big model; merging the transportation scheduling route scheduling strategy and the terminal freight hub scheduling strategy of the current transportation tool to obtain the transportation scheduling strategy for the current transportation tool; and optimizing the transportation path and freight hub selection of the transportation tool, reducing transportation costs, improving transportation efficiency, and enhancing transportation reliability and competitiveness.

Description

Technical Field

[0001] The present invention relates to the technical field of scheduling management, and in particular to an intelligent scheduling method and system based on an artificial intelligence large model. Background Art

[0002] In today's wave of digital and intelligent industrial development, industrial cloud computing, industrial cloud platforms, and industrial internet platforms are becoming key drivers of industrial transformation and upgrading. With the continuous development of the manufacturing industry and the increasing closeness of global trade, businesses are increasingly demanding higher standards for production efficiency, quality control, and supply chain management. In the transportation sector, vehicle scheduling is a critical link in ensuring safe, efficient, and economical transportation. With the continuous growth of global trade, the scale and complexity of transportation are increasing, and the requirements for vehicle scheduling are also becoming increasingly stringent. Traditional vehicle scheduling methods rely primarily on manual experience and limited data, making them difficult to cope with the changing transportation environment, complex transportation routing, and diverse cargo and freight hub requirements. With the advancement of information technology, transportation vehicles are equipped with a variety of advanced sensor devices, capable of collecting large amounts of sensor data and transportation environment data in real time. At the same time, information on transportation routes, cargo, freight hubs, and coordination between vehicles in the same space has become richer and more accurate. Furthermore, in terms of production collaboration, transportation scheduling requires close coordination with numerous other links. Vehicle scheduling must be coordinated with the production schedule and storage capacity of goods to avoid cargo backlogs and idle transportation resources. At the same time, coordination with loading and unloading operations at freight hubs is necessary to optimize the time transport vehicles spend at these hubs. Furthermore, efficient collaboration between different transport vehicles in the same space is essential to achieve optimal resource allocation and improve the operational efficiency of the entire transportation system. However, effectively integrating and analyzing this massive amount of multi-source, heterogeneous data to generate scientifically sound scheduling strategies remains a significant challenge.

[0003] Current transportation scheduling lacks full utilization and in-depth analysis of real-time data, making it difficult to achieve dynamic and accurate scheduling decisions. At the same time, the lack of coordination between information from different cloud platforms results in less-than-ideal coordination and adaptability of scheduling solutions, impacting transportation efficiency and safety. Existing scheduling methods struggle to efficiently integrate complex data from multiple sources, impacting the comprehensiveness of scheduling strategies. When generating scheduling strategies, insufficient consideration is given to information such as the coordination of transportation vehicles in the same space, making it impossible to adjust scheduling strategies in a timely manner based on real-time changes. This results in insufficient timeliness of the strategies, ultimately impacting production scheduling and preventing improvements in production efficiency. This is especially true when emergency scheduling is required, as it prevents further improvements in emergency response capabilities.

[0004] Therefore, the present invention proposes an intelligent scheduling method and system based on an artificial intelligence big model. Summary of the Invention

[0005] The present invention provides an intelligent scheduling method and system based on an artificial intelligence large model, which is used to provide a rich data basis for generating accurate and effective scheduling strategies by collecting comprehensive information such as transportation tool sensor data and transportation space environment data. The transportation scheduling route scheduling strategy for transportation tools generated based on the artificial intelligence large model can fully utilize the powerful computing and analysis capabilities of the large model to formulate a more scientific and reasonable transportation scheduling route plan. The terminal freight hub scheduling strategy is generated based on cargo information, freight hub information, etc., which improves the pertinence and efficiency of freight hub scheduling. The transportation scheduling route scheduling strategy and the terminal freight hub scheduling strategy are merged to form a complete transportation scheduling strategy, making the scheduling plan more comprehensive and comprehensive, and ensuring the efficiency and safety of transportation tools. This intelligent scheduling method can optimize the transportation path and freight hub selection of transportation tools, reduce transportation costs, improve transportation efficiency, and enhance transportation reliability and competitiveness.

[0006] The present invention provides an intelligent scheduling method based on an artificial intelligence large model, comprising:

[0007] S1: Collect current transport tool sensor data, transport space environment data, transport scheduling route information, cargo information, freight hub information, and co-location information of transport tools in the same space;

[0008] S2: Generates a transportation scheduling route scheduling strategy for the current transportation tool based on the current transportation tool sensor data, transportation space environment data, transportation scheduling route information, cargo information, coordination information of transportation tools in the same space, and the artificial intelligence big model;

[0009] S3: Generates the terminal freight hub scheduling strategy for the current transport tool based on the current cargo information, freight hub information, information on the coordination of transport tools in the same space, and the artificial intelligence big model;

[0010] S4: The transportation scheduling route scheduling strategy of the current transportation tool and the terminal freight hub scheduling strategy are combined to obtain the transportation scheduling strategy of the current transportation tool.

[0011] Preferably, the intelligent scheduling method based on the artificial intelligence large model, S1: collects current transportation tool sensor data, transportation space environment data, transportation scheduling route information, cargo information, freight hub information, and same-space transportation tool collaboration information, including:

[0012] Collecting the current position, current speed, current direction, and current state parameters of the current transport tool as current transport tool sensor data;

[0013] Determine a current transport space environment monitoring area based on the current position of the current transport vehicle, and collect transport space environment data within the current transport space environment monitoring area;

[0014] Collect the terminal location information of the current transportation tool, the freight hub information passed through, and the transportation scheduling route restriction conditions as the current transportation scheduling route information;

[0015] Collect the type of cargo, cargo weight, and loading and unloading requirements of the current transport vehicle as current cargo information;

[0016] Collect the capacity distribution information and loading and unloading equipment status information of all terminal freight hubs of the current transportation means as the current freight hub information;

[0017] Based on high-frequency wireless communication, the collaborative information of all the same-space transportation tools of the current transportation tool is collected as the same-space transportation tool collaborative information.

[0018] Preferably, the intelligent scheduling method based on the artificial intelligence big model, S2: generating a transportation scheduling route scheduling strategy for the current transportation tool based on the current transportation tool sensor data, transportation space environment data, transportation scheduling route information, same-space transportation tool collaboration information, and the artificial intelligence big model, including:

[0019] Determine the minimum scheduling boundary location information of the terminal freight hub group based on the terminal location information in the current transportation scheduling route information;

[0020] Build an intelligent model for transportation scheduling and route planning;

[0021] Input the current transport tool sensor data, transport space environment data, and transport scheduling route information into the transport scheduling route planning intelligent model to obtain the initial planned transport scheduling route for the current transport tool;

[0022] Based on the collaborative information of the same-space transportation tools, the initial planned transportation scheduling routes of all the same-space transportation tools of the current transportation tool are obtained;

[0023] Based on the initial planned transportation scheduling route of the current transportation tool and the initial planned transportation scheduling routes of all transportation tools in the same space as the current transportation tool, a transportation scheduling route scheduling strategy for the current transportation tool is generated.

[0024] Preferably, the intelligent scheduling method based on the artificial intelligence large model generates a scheduling strategy for the transportation scheduling route of the current transportation tool based on the initial planned transportation scheduling route of the current transportation tool and the initial planned transportation scheduling routes of all transportation tools in the same space as the current transportation tool, including:

[0025] Dynamically simulate the initial planned transportation scheduling route of the current transportation tool based on the current transportation tool sensor data, transportation space environment data, and transportation scheduling route information to obtain the initial planned dynamic transportation scheduling route of the current transportation tool;

[0026] Dynamically simulate the initial planned transportation scheduling route of the corresponding same-space transportation tool based on the transportation tool sensor data, transportation space environment data, and transportation scheduling route information of each same-space transportation tool of the current transportation tool to obtain the initial planned dynamic transportation scheduling route of each same-space transportation tool of the current transportation tool;

[0027] Determine whether the initial planned dynamic transport scheduling route of the current transport tool intersects with the initial planned dynamic transport scheduling routes of all transport tools in the same space as the current transport tool. If so, optimize the initial planned dynamic transport scheduling route of the current transport tool or the initial planned dynamic transport scheduling routes of all transport tools in the same space as the current transport tool to obtain the transport scheduling route scheduling strategy of the current transport tool. Otherwise, generate the transport scheduling route scheduling strategy of the current transport tool based on the initial planned dynamic transport scheduling route of the current transport tool.

[0028] Preferably, the intelligent scheduling method based on the artificial intelligence large model optimizes the initial planned dynamic transportation scheduling route of the current transportation tool or the initial planned dynamic transportation scheduling routes of all transportation tools in the same space as the current transportation tool to obtain the transportation scheduling route scheduling strategy of the current transportation tool, including:

[0029] All intersecting positions in the initial planned dynamic transport scheduling route of the current transport tool are regarded as all positions to be optimized, and the current transport tool and all transport tools in the same space that intersect at each position to be optimized in the corresponding initial planned dynamic transport scheduling route are regarded as candidate optimized transport tools for all transport scheduling routes at each position to be optimized;

[0030] Based on the transport tool sensor data, transport space environment data, and transport scheduling route information of all transport scheduling route alternative optimization transport tools at each location to be optimized, the degree to which the transport scheduling routes of all transport scheduling route alternative optimization transport tools at the corresponding location to be optimized are calculated;

[0031] All transport scheduling route alternative optimization transport means, except the transport scheduling route alternative optimization transport means with the minimum transport scheduling route optimization degree, among all transport scheduling route alternative optimization transport means of each location to be optimized are regarded as the target transport scheduling route optimization transport means of each location to be optimized;

[0032] Based on all positions to be optimized, the initial planned dynamic transportation scheduling route of the transportation tool corresponding to the target transportation scheduling route is optimized to avoid the transportation scheduling route, and the final planned dynamic transportation scheduling route of the current transportation tool is obtained as the transportation scheduling route scheduling strategy of the current transportation tool.

[0033] Preferably, the intelligent scheduling method based on the artificial intelligence large model calculates the degree of optimization of the transportation scheduling routes of all the alternative optimization transportation vehicles for each location to be optimized based on the transportation vehicle sensor data, transportation space environment data, and transportation scheduling route information of all the alternative optimization transportation vehicles for each location to be optimized, including:

[0034] Calculate the degree of optimizability of the first transport scheduling route of each transport scheduling route alternative optimization transport tool at each location to be optimized based on the transport tool sensor data, transport space environment data, and transport scheduling route information of all transport scheduling route alternative optimization transport tools at each location to be optimized;

[0035] Calculate the degree of optimizability of the second transport scheduling route of each transport scheduling route alternative optimization transport tool at the corresponding position to be optimized based on the driving direction and driving speed of all transport scheduling route alternative optimization transport tools at each position to be optimized;

[0036] Based on the first transport scheduling route optimizability degree and the second transport scheduling route optimizability degree of each transport scheduling route alternative optimization transport tool at each location to be optimized, the transport scheduling route optimizability degree of all transport scheduling route alternative optimization transport tools at each location to be optimized is calculated.

[0037] Preferably, the intelligent scheduling method based on the artificial intelligence large model calculates the degree of optimisation of the second transport scheduling route of each transport scheduling route alternative optimization transport tool at each location to be optimized based on the driving direction and driving speed of all transport scheduling route alternative optimization transport tools at the corresponding location to be optimized, including:

[0038]

[0039] Where, OD R2 is the degree of optimizability of the second transport scheduling route of the currently calculated transport scheduling route alternative optimized transport tool at the currently calculated position to be optimized, v max The maximum speed that can be achieved by the alternative optimized transport vehicle for the currently calculated transport scheduling route, v hThe speed of the alternative optimized transport vehicle for the currently calculated transport scheduling route at the currently calculated location to be optimized, C up The speed-up cost of the alternative transportation tool for the currently calculated transportation scheduling route is optimized, v min The minimum travel speed that can be achieved by the alternative optimized transport vehicle for the currently calculated transport scheduling route, C down is the deceleration cost of the alternative optimized transportation tool for the currently calculated transportation scheduling route, α1 is the driving speed optimization weight, a h1 If there are only two alternative transportation tools for the transportation scheduling route of the location to be optimized, the driving direction of the first alternative transportation tool for the transportation scheduling route is a, h2 If there are only two alternative transportation tools for the transportation scheduling route of the location to be optimized, the driving direction of the second alternative transportation tool for the transportation scheduling route is I(a h1 ,a h2 ) is the angle between the driving directions of the two alternative optimized transportation tools of the transportation scheduling route when there are only two alternative optimized transportation tools of the transportation scheduling route for the location to be optimized. α2 is the driving direction optimization weight. n is the total number of alternative optimized transportation tools of the transportation scheduling route for the location to be optimized. h0 Optimize the driving direction of the transport tool for the currently calculated transport scheduling route alternative, a hi The driving direction of the i-th transport scheduling route alternative optimization transport tool among all the transport scheduling route alternative optimization transport tools of the currently calculated position to be optimized, except the currently calculated transport scheduling route alternative optimization transport tool, and i = 3, 4, 5 ..., n, max[I(a h0 ,a hi )] is the maximum value of the angles between the driving direction of the currently calculated alternative optimized transport means for the transport scheduling route and the driving directions of all alternative optimized transport means for the currently calculated transport scheduling route for the position to be optimized except the currently calculated alternative optimized transport means for the transport scheduling route.

[0040] Preferably, the intelligent scheduling method based on the artificial intelligence big model, S3: based on the current cargo information, freight hub information, information on the coordination of transportation tools in the same space and the artificial intelligence big model, generates a terminal freight hub scheduling strategy for the current transportation tool, including:

[0041] Build an intelligent model for matching and evaluating loading and unloading requirements;

[0042] The cargo type and loading and unloading requirements in the current cargo information, as well as the loading and unloading equipment status information of each terminal freight hub of the current transportation vehicle, are input into the loading and unloading requirement matching evaluation intelligent model to obtain the current loading and unloading demand matching degree of each terminal freight hub;

[0043] Among all the terminal freight hubs of the current transport means, all terminal freight hubs whose current loading and unloading demand matching degree is not less than the loading and unloading demand matching degree threshold are regarded as all the current alternative freight hubs;

[0044] Based on current cargo information, current freight hub information, information on the coordination of transport vehicles in the same space, transport scheduling route scheduling strategies and artificial intelligence big models, the predicted busyness of each candidate freight hub is determined;

[0045] The freight hub with the lowest predicted busyness among all the current alternative freight hubs is selected as the target arrival freight hub;

[0046] Generate a destination freight hub scheduling strategy based on the target arrival freight hub.

[0047] Preferably, the intelligent scheduling method based on the artificial intelligence big model determines the current predicted busyness of each candidate freight hub based on current cargo information, current freight hub information, information on the coordination of transportation vehicles in the same space, the transportation scheduling route scheduling strategy, and the artificial intelligence big model, including:

[0048] Build an intelligent model for predicting freight hub busyness;

[0049] The current cargo information, current freight hub information, information on the coordination of transport tools in the same space, and transport scheduling route scheduling strategies are input into the freight hub busyness prediction intelligent model to obtain the current predicted busyness of each alternative freight hub.

[0050] The present invention provides an intelligent scheduling system based on an artificial intelligence big model, which is used to execute any of the above intelligent scheduling methods based on an artificial intelligence big model, including:

[0051] The information collection module is used to collect current transport tool sensor data, transport space environment data, transport scheduling route information, cargo information, freight hub information, and information on collaboration between transport tools in the same space;

[0052] The transport scheduling route scheduling module is used to generate the transport scheduling route scheduling strategy of the current transport tool based on the current transport tool sensor data, transport space environment data, transport scheduling route information, cargo information, co-space transport tool collaboration information and artificial intelligence large model;

[0053] The freight hub scheduling module is used to generate the terminal freight hub scheduling strategy of the current transport tool based on the current cargo information, freight hub information, the coordination information of the same space transport tools and the artificial intelligence big model;

[0054] The comprehensive scheduling module is used to combine the transportation scheduling route scheduling strategy of the current transportation tool and the terminal freight hub scheduling strategy to obtain the transportation scheduling strategy of the current transportation tool.

[0055] The beneficial effects of the present invention compared to the prior art are as follows: by collecting comprehensive information such as transport tool sensor data and transport space environment data, a rich data foundation is provided for generating accurate and effective scheduling strategies. The transport scheduling route scheduling strategy for transport tools generated based on the artificial intelligence large model can fully utilize the powerful computing and analysis capabilities of the large model to formulate a more scientific and reasonable transport scheduling route plan. The terminal freight hub scheduling strategy is generated based on cargo information, freight hub information, etc., which improves the pertinence and efficiency of freight hub scheduling. The transport scheduling route scheduling strategy and the terminal freight hub scheduling strategy are merged to form a complete transport scheduling strategy, making the scheduling plan more comprehensive and comprehensive, and ensuring the efficiency and safety of transport tool travel. This intelligent scheduling method can optimize the transport path and freight hub selection of transport tools, reduce transportation costs, improve transportation efficiency, enhance transportation reliability and competitiveness, and especially when emergency scheduling is required, it can further enhance emergency response capabilities.

[0056] Other features and advantages of the present invention will be described in the following description, and in part will become apparent from the description, or will be understood by practicing the present invention. The purpose and other advantages of the present invention can be achieved and obtained through the structures specifically pointed out in this application document.

[0057] The technical solution of the present invention is further described in detail below through the accompanying drawings and embodiments. BRIEF DESCRIPTION OF THE DRAWINGS

[0058] The accompanying drawings are used to provide a further understanding of the present invention and constitute a part of the specification. Together with the embodiments of the present invention, they are used to explain the present invention and do not constitute a limitation of the present invention. In the accompanying drawings:

[0059] Figure 1 This is a flow chart of an intelligent scheduling method based on an artificial intelligence large model in an embodiment of the present invention;

[0060] Figure 2 This is a diagram of the internal functional modules of the intelligent scheduling system based on the artificial intelligence big model in an embodiment of the present invention. DETAILED DESCRIPTION

[0061] The preferred embodiments of the present invention are described below with reference to the accompanying drawings. It should be understood that the preferred embodiments described herein are only used to illustrate and explain the present invention, and are not used to limit the present invention.

[0062] Example 1:

[0063] The present invention provides an intelligent scheduling method based on an artificial intelligence large model. Figure 1 ,include:

[0064] S1: Collect current transport tool sensor data, transport space environment data, transport scheduling route information, cargo information, freight hub information, and co-location information of transport tools in the same space;

[0065] S2: Generates a transportation scheduling route scheduling strategy for the current transportation tool based on the current transportation tool sensor data, transportation space environment data, transportation scheduling route information, cargo information, coordination information of transportation tools in the same space, and the artificial intelligence big model;

[0066] S3: Generates the terminal freight hub scheduling strategy for the current transport tool based on the current cargo information, freight hub information, information on the coordination of transport tools in the same space, and the artificial intelligence big model;

[0067] S4: The transportation scheduling route scheduling strategy of the current transportation tool and the terminal freight hub scheduling strategy are combined to obtain the transportation scheduling strategy of the current transportation tool.

[0068] In this embodiment, the artificial intelligence big model is a complex intelligent model with powerful computing and analysis capabilities, which can process and integrate a large amount of transportation tool related data to provide support for generating scheduling strategies.

[0069] In this embodiment, the transportation scheduling route scheduling strategy of the current transportation tool refers to the travel route arrangement planned for the current transportation tool based on various relevant data and model analysis, including decisions on the starting point, waypoints, end point, and travel speed.

[0070] In this embodiment, the terminal freight hub scheduling strategy of the current transport vehicle is a strategy for determining the final stop at the freight hub for the current transport vehicle based on the cargo, freight hub and collaborative information, including which freight hub is selected as the final destination and the arrival time.

[0071] In this embodiment, the transportation scheduling strategy of the current transportation tool is a complete scheduling plan formed by combining the transportation scheduling route scheduling strategy and the terminal freight hub scheduling strategy of the current transportation tool, covering key decisions such as the route and terminal freight hub during the entire driving process of the transportation tool.

[0072] The beneficial effects of the above technologies are: by collecting comprehensive information such as transport vehicle sensor data and transport space environment data, a rich data foundation is provided for generating accurate and effective scheduling strategies. Generating transport scheduling route scheduling strategies for transport vehicles based on artificial intelligence large models can fully utilize the powerful computing and analysis capabilities of large models to formulate more scientific and reasonable transport scheduling route plans. Generating terminal freight hub scheduling strategies based on cargo information, freight hub information, etc. improves the pertinence and efficiency of freight hub scheduling. Merging transport scheduling route scheduling strategies and terminal freight hub scheduling strategies to form a complete transport scheduling strategy makes the scheduling plan more comprehensive and comprehensive, ensuring the efficiency and safety of transport vehicle travel. This intelligent scheduling method can optimize the transportation routes and freight hub selection of transport vehicles, reduce transportation costs, improve transportation efficiency, and enhance transportation reliability and competitiveness.

[0073] Example 2:

[0074] Based on Example 1, the intelligent scheduling method based on the artificial intelligence large model, S1: collects current transportation tool sensor data, transportation space environment data, transportation scheduling route information, cargo information, freight hub information, and same-space transportation tool collaboration information, including:

[0075] Collecting the current position, current speed, current direction, and current state parameters of the current transport tool as current transport tool sensor data;

[0076] Determine the current transport space environment monitoring area based on the current position of the current transport vehicle, and collect altitude distribution data, wind direction and speed distribution data, and traffic speed and direction distribution data within the current transport space environment monitoring area as current transport space environment data;

[0077] Collect the terminal location information of the current transportation tool, the freight hub information passed through, and the transportation scheduling route restriction conditions as the current transportation scheduling route information;

[0078] Collect the type of cargo, cargo weight, and loading and unloading requirements of the current transport vehicle as current cargo information;

[0079] Collect the capacity distribution information and loading and unloading equipment status information of all terminal freight hubs of the current transportation means as the current freight hub information;

[0080] Based on high-frequency wireless communication, the collaborative information of all the same-space transportation tools of the current transportation tool is collected as the same-space transportation tool collaborative information.

[0081] In this embodiment, the current position of the current transportation means refers to the specific coordinates of the transportation means in the geographic space at the current moment.

[0082] In this embodiment, the current speed is the instantaneous speed at which the vehicle is currently traveling.

[0083] In this embodiment, the current direction is the direction in which the current transportation vehicle is traveling.

[0084] In this embodiment, the current transportation vehicle status parameters include parameters describing the status of the transportation vehicle itself, such as the equipment operating status of the transportation vehicle, the remaining fuel, and the structural integrity of the transportation vehicle.

[0085] In this embodiment, the current transportation space environment monitoring area is a transportation space area of ​​a specific range determined based on the current position of the current transportation tool, and is used to collect and analyze transportation space environment data of the area.

[0086] In this embodiment, the current transport space environment monitoring area is determined based on the current position of the current transport vehicle: a specific range of the transport space environment that needs to be monitored is defined according to the specific position of the current transport vehicle.

[0087] In this embodiment, the altitude distribution data, wind direction and speed distribution data, and vehicle speed and direction distribution data within the current transport space environment monitoring area are data obtained by measuring and recording the changes in altitude at different locations, the changes in wind direction and speed at different locations, and the changes in vehicle speed and direction at different locations within the designated current transport space environment monitoring area.

[0088] In this embodiment, the terminal location information of the current transport vehicle, the information of the freight hub along the way, and the transport scheduling route restriction conditions are:

[0089] The destination location information refers to the final destination of the transportation vehicle during this trip;

[0090] The transit freight hub information is the relevant information of the freight hubs where the transport vehicle plans to stop when reaching the destination;

[0091] Transport scheduling route restrictions include road width, channel depth, bridge height, tunnel height and other conditions that may restrict the route of transport vehicles.

[0092] In this embodiment, the type of cargo, cargo weight, and loading and unloading requirements of the current transport vehicle are:

[0093] Cargo type refers to the type of cargo carried on board the ship;

[0094] Cargo weight is the total weight of the cargo on board;

[0095] Loading and unloading requirements include the time, method, and equipment requirements for loading and unloading cargo.

[0096] In this embodiment, the capacity distribution information and loading and unloading equipment status information of all terminal freight hubs of the current transportation means are:

[0097] Capacity distribution information refers to the distribution of the number of transport vehicles and cargo storage capacity that each terminal freight hub can accommodate within the freight hub;

[0098] The status information of loading and unloading equipment includes whether the cranes, conveyor belts and other loading and unloading equipment at the freight hub are operating normally and their work efficiency.

[0099] In this embodiment, the same-space transportation means refers to other transportation means traveling in the same transportation space area as the current transportation means.

[0100] In this embodiment, collaborative information refers to information such as travel plans, locations, speeds, etc., which is exchanged and shared between transportation vehicles in the same space for the purpose of avoiding collisions, congestion, optimizing transportation scheduling routes, etc.

[0101] The beneficial effects of the above technologies include: Detailed collection of sensor data, including the current position, speed, direction, and status parameters of transport vehicles, provides a comprehensive understanding of the real-time status of the transport vehicles themselves, providing a foundation for precise scheduling. Determining the transport space environment monitoring area based on the vehicle's location and collecting relevant data, such as altitude, wind direction and speed, and traffic flow, helps fully consider the impact of the transport space environment on the vehicle's operation. Collecting transport route information, including destination locations, freight hubs involved, and route constraints, ensures that transport route planning is more aligned with actual needs and constraints. Detailed collection of cargo information, including cargo type, weight, and loading and unloading requirements, facilitates the rational arrangement of loading and unloading plans and transportation processes. Obtaining information about freight hubs, such as capacity distribution and loading and unloading equipment status, improves the efficiency and rationality of freight hub scheduling. High-frequency wireless communication is used to collect collaborative information from transport vehicles in the same space, enhancing inter-vehicle coordination and safety. This comprehensive, detailed, and accurate data collection method provides rich, reliable, and accurate data support for intelligent scheduling based on large AI models, helping to improve the scientific nature, efficiency, and safety of scheduling.

[0102] Example 3:

[0103] Based on Example 1, the intelligent scheduling method based on the artificial intelligence large model, S2: generating a transportation scheduling route scheduling strategy for the current transportation tool based on the current transportation tool sensor data, transportation space environment data, transportation scheduling route information, same-space transportation tool collaboration information, and the artificial intelligence large model, including:

[0104] Determine the minimum scheduling boundary location information of the terminal freight hub group based on the terminal location information in the current transportation scheduling route information;

[0105] Build an intelligent model for transportation scheduling and route planning;

[0106] Input the current transport tool sensor data, transport space environment data, and transport scheduling route information into the transport scheduling route planning intelligent model to obtain the initial planned transport scheduling route for the current transport tool;

[0107] Based on the collaborative information of the same-space transportation tools, the initial planned transportation scheduling routes of all the same-space transportation tools of the current transportation tool are obtained;

[0108] Based on the initial planned transportation scheduling route of the current transportation tool and the initial planned transportation scheduling routes of all transportation tools in the same space as the current transportation tool, a transportation scheduling route scheduling strategy for the current transportation tool is generated.

[0109] In this embodiment, the terminal freight hub group refers to a group of freight hubs whose final destinations are in similar areas.

[0110] In this embodiment, the minimum scheduling boundary location information is related information about the outermost location of the range covered by the terminal freight hub group, which is used for planning transportation scheduling routes and scheduling decisions.

[0111] In this embodiment, an intelligent model for transport scheduling route planning is built: an intelligent algorithm or system is created that can plan transport scheduling routes for transport vehicles based on various input data and conditions. Building an intelligent model for transport scheduling route planning generally requires the following steps and training samples:

[0112] Data collection: Collect a large amount of data related to the operation of transportation vehicles, including historical transportation vehicle sensor data, transportation space environment data, transportation scheduling route information, etc.

[0113] Feature engineering: Extract meaningful features from the collected data, such as the location, speed, and direction of the transportation vehicle, the characteristics of the transportation space environment, the starting point, end point, and transit points of the transportation scheduling route, and other features.

[0114] Select a model architecture: You can choose a model architecture suitable for processing sequence data and spatial data, such as recurrent neural network (RNN), long short-term memory network (LSTM), or graph neural network (GNN).

[0115] Train model: Use the prepared training data to train the model.

[0116] Training samples: Contains transportation vehicle driving data under various conditions, such as transportation vehicle sensor data, transportation space environment data, and actual transportation scheduling route information in different seasons, different weather conditions, and different cargo types and weights.

[0117] Contains driving samples of different types and sizes of transportation vehicles to meet the transportation scheduling route planning needs of multiple transportation vehicles.

[0118] Covers a variety of freight hubs and transport routing combinations, including busy freight hubs and less popular transport routings.

[0119] By using these rich and diverse training samples, the model can learn the optimal transportation scheduling route planning strategy under different situations, improving the model's generalization ability and accuracy.

[0120] In this embodiment, the initially planned transport scheduling route of the current transport means is a travel route preliminarily designed for the current transport means based on initial conditions and data.

[0121] In this embodiment, the initial planned transport scheduling routes of all transport tools in the same space of the current transport tool are obtained based on the collaborative information of transport tools in the same space: the collaborative information communicated and shared between other transport tools in the same space is used to obtain the preliminary set driving routes of these transport tools, which is mainly obtained by inputting the transport tool sensor data, transport space environment data, and transport scheduling route information of each transport tool in the same space contained in the collaborative information of transport tools in the same space into the transport scheduling route planning intelligent model.

[0122] The beneficial effects of the above technology include: determining the minimum scheduling boundary location information of the terminal freight hub cluster based on terminal location information, providing clear scope and constraints for transport scheduling route planning and improving planning accuracy. Building an intelligent transport scheduling route planning model can leverage the model's intelligent algorithms and learning capabilities to generate more optimized transport scheduling routes. Inputting multiple data into the model to obtain the initial planned transport scheduling route, fully considering multiple factors such as the vehicle's own status, the transportation space environment, and the transport scheduling route requirements. Obtaining the initial planned transport scheduling routes of other vehicles based on collaborative information of vehicles in the same space helps avoid transport scheduling route conflicts and improve the safety and efficiency of spatial travel. A transport scheduling route scheduling strategy is generated by comprehensively considering the initial planned transport scheduling routes of the current vehicle and those of the same vehicle in the same space, making the scheduling strategy more comprehensive, reasonable, and coordinated. This method can effectively plan safe, efficient, and coordinated transport scheduling route strategies for vehicles, improving transportation efficiency and safety and reducing travel risks and costs.

[0123] Example 4:

[0124] On the basis of Example 3, the intelligent scheduling method based on the artificial intelligence large model generates a scheduling strategy for the transportation scheduling route of the current transportation tool based on the initial planned transportation scheduling route of the current transportation tool and the initial planned transportation scheduling routes of all transportation tools in the same space as the current transportation tool, including:

[0125] Dynamically simulate the initial planned transportation scheduling route of the current transportation tool based on the current transportation tool sensor data, transportation space environment data, and transportation scheduling route information to obtain the initial planned dynamic transportation scheduling route of the current transportation tool;

[0126] Dynamically simulate the initial planned transportation scheduling route of the corresponding same-space transportation tool based on the transportation tool sensor data, transportation space environment data, and transportation scheduling route information of each same-space transportation tool of the current transportation tool to obtain the initial planned dynamic transportation scheduling route of each same-space transportation tool of the current transportation tool;

[0127] Determine whether the initial planned dynamic transport scheduling route of the current transport tool intersects with the initial planned dynamic transport scheduling routes of all transport tools in the same space as the current transport tool. If so, optimize the initial planned dynamic transport scheduling route of the current transport tool or the initial planned dynamic transport scheduling routes of all transport tools in the same space as the current transport tool to obtain the transport scheduling route scheduling strategy of the current transport tool. Otherwise, generate the transport scheduling route scheduling strategy of the current transport tool based on the initial planned dynamic transport scheduling route of the current transport tool.

[0128] In this embodiment, the initial planned transport scheduling route of the current transport tool is dynamically simulated based on the current transport tool sensor data, transport space environment data, and transport scheduling route information to obtain the initial planned dynamic transport scheduling route of the current transport tool: the data collected by the sensors of the current transport tool, the relevant data of the transport space environment in which it is located, and the initial planned transport scheduling route information are input into the simulation system. By considering various dynamic changing factors in actual driving, such as the speed of the transport tool, changes in the transport space environment, etc., a transport tool driving route that is closer to the actual situation is obtained, that is, the initial planned dynamic transport scheduling route.

[0129] In this embodiment, based on the transportation tool sensor data, transportation space environment data, and transportation scheduling route information of each transportation tool in the same space of the current transportation tool, the initial planned transportation scheduling route of the corresponding transportation tool in the same space is dynamically simulated to obtain the initial planned dynamic transportation scheduling route of each transportation tool in the same space of the current transportation tool: for each transportation tool in the same space, a similar dynamic simulation is performed based on its own sensor data, the transportation space environment conditions and the initial planned transportation scheduling route, so as to obtain its respective initial planned dynamic transportation scheduling route.

[0130] In this embodiment, a transport scheduling route scheduling strategy for the current transport tool is generated based on the initial planned dynamic transport scheduling route of the current transport tool: a final transport scheduling route arrangement decision, namely, a transport scheduling route scheduling strategy, is formulated based on the initial planned dynamic transport scheduling route of the current transport tool.

[0131] The beneficial effects of the above technology are: dynamic simulation of the initial planned transportation scheduling route of the current transportation tool can more realistically predict the transportation scheduling route situation, taking into account the influence of various dynamic factors. Dynamic simulation is also performed on the initial planned transportation scheduling routes of transportation tools in the same space to fully grasp the dynamics of the transportation scheduling routes in the space. By judging whether there is any intersection in the initial planned dynamic transportation scheduling routes, potential conflicts and risks can be discovered in a timely manner. Optimizing the dynamic transportation scheduling routes that have intersections effectively avoids transportation scheduling route conflicts and improves driving safety and efficiency. The generated transportation scheduling route scheduling strategy fully considers the relationship between dynamic situations and transportation tools, making scheduling more reasonable and reliable. This method of generating transportation scheduling route scheduling strategies through dynamic simulation and optimization can significantly improve the orderliness and safety of traffic, reduce the accident rate, and improve transportation efficiency and economic benefits.

[0132] Example 5:

[0133] On the basis of Example 4, the intelligent scheduling method based on the artificial intelligence large model optimizes the initial planned dynamic transportation scheduling route of the current transportation tool or the initial planned dynamic transportation scheduling routes of all transportation tools in the same space as the current transportation tool to obtain the transportation scheduling route scheduling strategy of the current transportation tool, including:

[0134] All intersecting positions in the initial planned dynamic transport scheduling route of the current transport tool are regarded as all positions to be optimized, and the current transport tool and all transport tools in the same space that intersect at each position to be optimized in the corresponding initial planned dynamic transport scheduling route are regarded as candidate optimized transport tools for all transport scheduling routes at each position to be optimized;

[0135] Based on the transport tool sensor data, transport space environment data, and transport scheduling route information of all transport scheduling route alternative optimization transport tools at each location to be optimized, the degree to which the transport scheduling routes of all transport scheduling route alternative optimization transport tools at the corresponding location to be optimized are calculated;

[0136] All transport scheduling route alternative optimization transport means, except the transport scheduling route alternative optimization transport means with the minimum transport scheduling route optimization degree, among all transport scheduling route alternative optimization transport means of each location to be optimized are regarded as the target transport scheduling route optimization transport means of each location to be optimized;

[0137] Based on all positions to be optimized, the initial planned dynamic transportation scheduling route of the transportation tool corresponding to the target transportation scheduling route is optimized to avoid the transportation scheduling route, and the final planned dynamic transportation scheduling route of the current transportation tool is obtained as the transportation scheduling route scheduling strategy of the current transportation tool.

[0138] In this embodiment, the degree to which the transport scheduling routes of all alternative optimized transport tools for each location to be optimized can be optimized at the corresponding location to be optimized refers to the degree to which the transport scheduling routes of all transport tools that can be selected for optimization are optimized at each location where there may be an intersection of transport scheduling routes that needs to be optimized, taking into account multiple factors such as the transport tool sensor data, transport space environment data, and transport scheduling route information, to evaluate the feasibility and benefits of changing the transport scheduling route at that location.

[0139] In this embodiment, the initial planned dynamic transport scheduling route of the transport tool corresponding to the target transport scheduling route is optimized based on all positions to be optimized, and the transport scheduling route avoidance optimization is performed to obtain the final planned dynamic transport scheduling route of the current transport tool as the transport scheduling route scheduling strategy of the current transport tool: for all positions that need to be optimized, the initial planned dynamic transport scheduling route of the target transport tool determined to need to adjust the transport scheduling route is optimized by taking measures to avoid intersections and conflicts, and the optimized driving route of the current transport tool is finally obtained, which is used as the transport scheduling route scheduling strategy of the current transport tool to guide the actual driving of the transport tool.

[0140] The beneficial effects of the above technology are as follows: treating intersection locations as locations to be optimized and identifying related transportation vehicles as alternative optimization transportation vehicles for the transportation scheduling route, accurately locating areas and objects requiring adjustment. The degree of optimization of the transportation scheduling route for the alternative optimization transportation vehicle for each location to be optimized is calculated, providing a quantitative basis for optimization decisions. Transportation vehicles other than those with the lowest degree of optimization are selected as target transportation scheduling route optimization transportation vehicles, making the optimization more targeted and reasonable. By performing transportation scheduling route avoidance optimization on the target transportation scheduling route optimization transportation vehicle based on all locations to be optimized, the problem of transportation scheduling route conflicts can be comprehensively resolved, ensuring safe and efficient driving. The final planned dynamic transportation scheduling route for the current transportation vehicle is obtained as the transportation scheduling route scheduling strategy, which can effectively improve the rationality and adaptability of the transportation scheduling route. This refined transportation scheduling route optimization method can minimize transportation scheduling route conflicts, improve driving efficiency and safety, and reduce energy consumption and transportation costs.

[0141] Example 6:

[0142] On the basis of Example 5, the intelligent scheduling method based on the artificial intelligence large model calculates the degree of optimization of the transportation scheduling routes of all the alternative optimization transportation vehicles for each location to be optimized based on the transportation vehicle sensor data, transportation space environment data, and transportation scheduling route information of all the alternative optimization transportation vehicles for each location to be optimized, including:

[0143] Calculate the degree of optimizability of the first transport scheduling route of each transport scheduling route alternative optimization transport tool at each location to be optimized based on the transport tool sensor data, transport space environment data, and transport scheduling route information of all transport scheduling route alternative optimization transport tools at each location to be optimized;

[0144] Calculate the degree of optimizability of the second transport scheduling route of each transport scheduling route alternative optimization transport tool at the corresponding position to be optimized based on the driving direction and driving speed of all transport scheduling route alternative optimization transport tools at each position to be optimized;

[0145] Based on the first transport scheduling route optimizability degree and the second transport scheduling route optimizability degree of each transport scheduling route alternative optimization transport tool at each location to be optimized, the transport scheduling route optimizability degree of all transport scheduling route alternative optimization transport tools at each location to be optimized is calculated.

[0146] In this embodiment, based on the transport tool sensor data, transport space environment data, and transport scheduling route information of all transport scheduling route alternative optimization transport tools at each location to be optimized, the degree to which the first transport scheduling route of each transport scheduling route alternative optimization transport tool at each location to be optimized can be optimized at the corresponding location to be optimized: at each location where the transport scheduling route needs to be optimized, for each transport tool that can be used as an adjustment object, its own sensor data (such as transport tool status), the transport space environment conditions in which it is located, and the original transport scheduling route planning and other information are combined to evaluate the preliminary feasibility of adjusting the transport scheduling route of this transport tool at that location.

[0147] In this embodiment, the degree to which the first transport scheduling route of each alternative optimized transport tool for each transport scheduling route at each location to be optimized can be optimized at the corresponding location to be optimized refers to the quantitative value of the feasibility of the preliminary transport scheduling route adjustment of a certain alternative optimized transport tool at a specific location to be optimized, evaluated based on the partial data and information mentioned above.

[0148] In this embodiment, the degree to which the alternative optimized transport tool of each transport scheduling route at each location to be optimized can be optimized in the second transport scheduling route corresponding to the location to be optimized: at each location to be optimized, for each alternative optimized transport tool, another quantitative value of the feasibility of transport scheduling route adjustment is obtained by further evaluating factors such as its driving direction and driving speed.

[0149] In this embodiment, the transport scheduling route optimizability of all transport scheduling route alternative optimization transport tools at each position to be optimized is calculated based on the first transport scheduling route optimizability and the second transport scheduling route optimizability of each transport scheduling route alternative optimization transport tool at the corresponding position to be optimized: taking into account the quantitative values ​​of the above two transport scheduling route optimizability of each transport tool at each position to be optimized, a comprehensive quantitative value of the feasibility of the overall transport scheduling route adjustment of all alternative optimization transport tools at the position is obtained through a specific calculation method (for example, calculating the average value of the two) or weight distribution.

[0150] The beneficial effects of the above technology include: calculating the degree of optimisation of the first transport scheduling route of each transport scheduling route alternative optimization transport tool for each location to be optimized based on a variety of data, comprehensively considering multiple factors such as the transport tool itself and the environment, making the optimization evaluation more comprehensive. Calculating the degree of optimisation of the second transport scheduling route based on the driving direction and speed, and further evaluating the possibility and difficulty of optimization from a dynamic perspective. Calculating the final degree of optimisation of the transport scheduling route by combining the degrees of optimisation of the first and second transport scheduling routes makes the evaluation results more accurate and comprehensive. This multi-dimensional and detailed calculation method can more accurately determine the potential and difficulty of transport scheduling route adjustment for each transport tool at the location to be optimized. It helps to formulate a more scientific and reasonable transport scheduling route optimization plan, minimize transport scheduling route conflicts, and improve the efficiency and safety of transport scheduling route scheduling. It provides a reliable quantitative basis and technical support for generating efficient, safe and adaptable transport scheduling route scheduling strategies.

[0151] Example 7:

[0152] On the basis of Example 6, the intelligent scheduling method based on the artificial intelligence large model calculates the degree of optimizability of the second transport scheduling route of each transport scheduling route alternative optimization transport tool at the corresponding position to be optimized based on the driving direction and driving speed of all transport scheduling route alternative optimization transport tools at each position to be optimized, including:

[0153]

[0154] Where, OD R2 is the degree of optimizability of the second transport scheduling route of the currently calculated transport scheduling route alternative optimized transport tool at the currently calculated position to be optimized, v max The maximum speed that can be achieved by the alternative optimized transport vehicle for the currently calculated transport scheduling route, v h The speed of the alternative optimized transport vehicle for the currently calculated transport scheduling route at the currently calculated location to be optimized, Cup The speed-up cost of the alternative optimized transportation tool for the currently calculated transportation scheduling route, v min The minimum travel speed that can be achieved by the alternative optimized transport vehicle for the currently calculated transport scheduling route, C down is the deceleration cost of the alternative optimized transportation tool for the currently calculated transportation scheduling route, α1 is the driving speed optimization weight, a h1 If there are only two alternative transportation tools for the transportation scheduling route of the location to be optimized, the driving direction of the first alternative transportation tool for the transportation scheduling route is a, h2 If there are only two alternative transportation tools for the transportation scheduling route of the location to be optimized, the driving direction of the second alternative transportation tool for the transportation scheduling route is I(a h1 ,a h2 ) is the angle between the driving directions of the two alternative optimized transportation tools of the transportation scheduling route when there are only two alternative optimized transportation tools of the transportation scheduling route for the location to be optimized. α2 is the driving direction optimization weight. n is the total number of alternative optimized transportation tools of the transportation scheduling route for the location to be optimized. h0 Optimize the driving direction of the transport tool for the currently calculated transport scheduling route alternative, a hi The driving direction of the i-th transport scheduling route alternative optimization transport tool among all the transport scheduling route alternative optimization transport tools of the currently calculated position to be optimized, except the currently calculated transport scheduling route alternative optimization transport tool, and i = 3, 4, 5 ..., n, max[I(a h0 ,a hi )] is the maximum value of the angles between the driving direction of the currently calculated alternative optimized transport means for the transport scheduling route and the driving directions of all alternative optimized transport means for the currently calculated transport scheduling route for the position to be optimized except the currently calculated alternative optimized transport means for the transport scheduling route.

[0155] In this embodiment, the maximum (minimum) driving speed that the currently calculated alternative optimized transport vehicle for the transport scheduling route can reach refers to the upper (lower) limit of the highest (lowest) driving speed that the alternative optimized transport vehicle currently being analyzed and calculated can reach.

[0156] In this embodiment, the speed-increasing (reducing) cost of the alternative optimized transportation tool of the currently calculated transportation scheduling route is the price that the alternative optimized transportation tool currently under consideration needs to pay to increase (reduce) the driving speed, which may include costs in terms of energy consumption, mechanical loss, etc.

[0157] In this embodiment, the driving speed optimization weight is a numerical value indicating the relative importance of the driving speed factor when calculating the degree of optimization of the transportation scheduling route.

[0158] All angles in this embodiment are acute angles between two directions, and the unit of the angle is rad.

[0159] In this embodiment, the driving direction optimization weight is a numerical value indicating the relative importance of the driving direction factor when calculating the degree of optimization of the transportation scheduling route.

[0160] The beneficial effects of the above technology are: by calculating the degree of optimization of the second transport scheduling route through a clear mathematical formula, the impact of driving speed and driving direction on the optimization of the transport scheduling route can be accurately quantified. Factors such as the maximum driving speed, minimum driving speed, speed-up cost, and speed-down cost of the transport vehicle are taken into account, making the optimization evaluation of speed more comprehensive and practical. The introduction of driving speed optimization weights and driving direction optimization weights can flexibly adjust the importance of speed and direction in the optimization degree calculation. For the calculation of driving direction, the directional angles between multiple transport vehicles are comprehensively considered, accurately reflecting the effect of directional factors on the optimization of transport scheduling routes. This precise and comprehensive calculation method can provide a scientific and accurate basis for the optimization of transport scheduling routes, and help to formulate more reasonable and efficient transport scheduling route scheduling strategies. It improves the accuracy and effect of transport scheduling route optimization, enhances driving safety and efficiency, and reduces the risk of transport scheduling route conflicts.

[0161] Example 8:

[0162] Based on Example 1, the intelligent scheduling method based on the artificial intelligence large model, S3: Based on the current cargo information, freight hub information, information about the coordinated transportation tools in the same space, and the artificial intelligence large model, a terminal freight hub scheduling strategy for the current transportation tool is generated, including:

[0163] Build an intelligent model for matching and evaluating loading and unloading requirements;

[0164] The cargo type and loading and unloading requirements in the current cargo information, as well as the loading and unloading equipment status information of each terminal freight hub of the current transportation vehicle, are input into the loading and unloading requirement matching evaluation intelligent model to obtain the current loading and unloading demand matching degree of each terminal freight hub;

[0165] Among all the terminal freight hubs of the current transport means, all terminal freight hubs whose current loading and unloading demand matching degree is not less than the loading and unloading demand matching degree threshold are regarded as all the current alternative freight hubs;

[0166] Based on current cargo information, current freight hub information, information on the coordination of transport vehicles in the same space, transport scheduling route scheduling strategies and artificial intelligence big models, the predicted busyness of each candidate freight hub is determined;

[0167] The freight hub with the lowest predicted busyness among all the current alternative freight hubs is selected as the target arrival freight hub;

[0168] Generate a destination freight hub scheduling strategy based on the target arrival freight hub.

[0169] In this embodiment, an intelligent model for evaluating the matching of loading and unloading requirements is built: an intelligent model is created that can evaluate the degree of matching between cargo loading and unloading requirements and the loading and unloading capacity of the freight hub based on input information such as the type of cargo, loading and unloading requirements, and the status of the loading and unloading equipment at the freight hub. Technologies such as neural networks can be used to build an intelligent model for evaluating the matching of loading and unloading requirements. The training samples should contain rich and diverse information. First, there must be data on the detailed types, weights, special loading and unloading requirements, etc. of various types of cargo. Secondly, information such as the types, quantities, performance, and maintenance status of loading and unloading equipment at different freight hubs should be covered. At the same time, historical loading and unloading operation data of freight hubs under different time periods (such as holidays, peak seasons, and off-seasons) and different weather conditions should be included. It is also necessary to include records of the actual matching effects of different cargoes and different freight hub loading and unloading equipment combinations, as well as data on the impact of freight hub personnel configuration and work processes on loading and unloading, so that the model can accurately evaluate the matching degree.

[0170] In this embodiment, the current loading and unloading demand matching degree of each terminal freight hub is: for each freight hub serving as the destination of travel, a quantitative value is used to measure the degree to which the conditions such as the status of its loading and unloading equipment meet the cargo loading and unloading requirements of the current transport vehicle.

[0171] In this embodiment, the loading and unloading demand matching threshold is a pre-set standard value used to determine whether the loading and unloading demand matching degree of the terminal freight hub is qualified.

[0172] In this embodiment, the predicted busyness of each current candidate freight hub is: for each freight hub currently listed as a candidate, a quantitative estimate of its busyness in the future period predicted by a model or algorithm.

[0173] In this embodiment, the target arrival freight hub is: a freight hub selected as the final stop destination of the transportation vehicle from among all candidate freight hubs based on factors such as predicted busyness.

[0174] In this embodiment, a terminal freight hub scheduling strategy is generated based on the target arrival freight hub: according to the determined target arrival freight hub, a freight hub scheduling plan including arrival time, docking arrangement, etc. is formulated.

[0175] The beneficial effects of the above technologies include: An intelligent model for evaluating loading and unloading requirement matching is established, which utilizes intelligent algorithms to accurately assess the degree of match between cargo loading and unloading requirements and the status of freight hub loading and unloading equipment. The model determines the degree of matching between loading and unloading requirements at each terminal freight hub, providing a quantitative basis for selecting suitable freight hubs. Terminal freight hubs with loading and unloading requirement matching scores no less than a threshold are selected as candidate freight hubs, improving the accuracy and reliability of freight hub selection. The predicted busyness of each candidate freight hub is determined based on multiple information sources, fully considering various factors affecting freight hub operational efficiency. The candidate with the lowest predicted busyness is selected as the target arrival freight hub, minimizing waiting times and improving transportation efficiency. A terminal freight hub scheduling strategy is generated based on the target arrival freight hub, making the scheduling strategy more targeted and optimized. This method enables efficient and accurate terminal freight hub scheduling, reducing transportation costs, improving the timeliness of cargo transportation, and enhancing the utilization of freight hub resources.

[0176] Example 9:

[0177] Based on Example 8, the intelligent scheduling method based on the artificial intelligence big model determines the current predicted busyness of each candidate freight hub based on current cargo information, current freight hub information, information about co-location transport tools, transportation scheduling route scheduling strategy, and the artificial intelligence big model, including:

[0178] Build an intelligent model for predicting freight hub busyness;

[0179] The current cargo information, current freight hub information, information on the coordination of transport tools in the same space, and transport scheduling route scheduling strategies are input into the freight hub busyness prediction intelligent model to obtain the current predicted busyness of each alternative freight hub.

[0180] In this embodiment, building an intelligent model for predicting the busyness of a freight hub refers to creating an intelligent algorithm or system that can predict the future busyness of a freight hub based on input information such as current cargo information, freight hub information, information about the coordination of transport vehicles in the same space, and transportation scheduling routes and scheduling strategies. Deep learning technology can be used to build an intelligent model for predicting the busyness of a freight hub. During the training process, the model inputs include the historical cargo flow of the freight hub, the type of cargo, the time and number of transport vehicles entering and leaving the freight hub, the status of the freight hub equipment, weather conditions, information about the coordination of transport vehicles in the same space, and the current transportation scheduling routes and scheduling strategies. The model output is a predicted value for the busyness of the freight hub over a period of time in the future, which may be presented in the form of a specific busyness value or busyness level, so as to provide a decision-making basis for freight hub scheduling.

[0181] The beneficial effects of the above technologies include: building an intelligent model for predicting freight hub busyness, which can be used to predict busyness using a specialized model, improving the professionalism and accuracy of the predictions. By inputting a variety of relevant information into the model, comprehensive factors such as cargo, freight hubs, coordination of co-located transportation vehicles, and transportation scheduling route scheduling strategies are fully considered, making the prediction results more comprehensive and reliable. The model obtains the predicted busyness of each alternative freight hub, providing accurate data support for selecting the optimal target arrival freight hub. This prediction method based on comprehensive information and intelligent models helps to improve the efficiency and rationality of freight hub scheduling and reduce congestion and waiting times at freight hubs. It can better plan the selection of terminal freight hubs for transportation vehicles, improving the overall efficiency and economic benefits of freight transportation.

[0182] Example 10:

[0183] The present invention provides an intelligent scheduling system based on an artificial intelligence big model, which is used to execute any one of the intelligent scheduling methods based on an artificial intelligence big model in embodiments 1 to 9, with reference to Figure 2 ,include:

[0184] The information collection module is used to collect current transport tool sensor data, transport space environment data, transport scheduling route information, cargo information, freight hub information, and information on collaboration between transport tools in the same space;

[0185] The transport scheduling route scheduling module is used to generate the transport scheduling route scheduling strategy of the current transport tool based on the current transport tool sensor data, transport space environment data, transport scheduling route information, cargo information, co-space transport tool collaboration information and artificial intelligence large model;

[0186] The freight hub scheduling module is used to generate the terminal freight hub scheduling strategy of the current transport tool based on the current cargo information, freight hub information, the coordination information of the same space transport tools and the artificial intelligence big model;

[0187] The comprehensive scheduling module is used to combine the transportation scheduling route scheduling strategy of the current transportation tool and the terminal freight hub scheduling strategy to obtain the transportation scheduling strategy of the current transportation tool.

[0188] The beneficial effects of the above technologies are: by collecting comprehensive information such as transport vehicle sensor data and transport space environment data, a rich data foundation is provided for generating accurate and effective scheduling strategies. Generating transport scheduling route scheduling strategies for transport vehicles based on artificial intelligence large models can fully utilize the powerful computing and analysis capabilities of large models to formulate more scientific and reasonable transport scheduling route plans. Generating terminal freight hub scheduling strategies based on cargo information, freight hub information, etc. improves the pertinence and efficiency of freight hub scheduling. Merging transport scheduling route scheduling strategies and terminal freight hub scheduling strategies to form a complete transport scheduling strategy makes the scheduling plan more comprehensive and comprehensive, ensuring the efficiency and safety of transport vehicle travel. This intelligent scheduling method can optimize the transportation routes and freight hub selection of transport vehicles, reduce transportation costs, improve transportation efficiency, and enhance transportation reliability and competitiveness.

[0189] Obviously, those skilled in the art may make various changes and modifications to the present invention without departing from the spirit and scope of the present invention. Thus, if such changes and modifications fall within the scope of the claims and their equivalents, the present invention is intended to include such changes and modifications.

Claims

1. An intelligent scheduling method based on an artificial intelligence large model, characterized in that: include: S1: Collect current transport tool sensor data, transport space environment data, transport scheduling route information, cargo information, freight hub information, and co-location information of transport tools in the same space; S2: Determine the minimum scheduling boundary location information of the terminal freight hub group based on the terminal location information in the current transportation scheduling route information; Build an intelligent model for transportation scheduling and route planning; Input the current transport tool sensor data, transport space environment data, and transport scheduling route information into the transport scheduling route planning intelligent model to obtain the initial planned transport scheduling route for the current transport tool; Based on the collaborative information of the same-space transportation tools, the initial planned transportation scheduling routes of all the same-space transportation tools of the current transportation tool are obtained; Dynamically simulate the initial planned transportation scheduling route of the current transportation tool based on the current transportation tool sensor data, transportation space environment data, and transportation scheduling route information to obtain the initial planned dynamic transportation scheduling route of the current transportation tool; Dynamically simulate the initial planned transportation scheduling route of the corresponding same-space transportation tool based on the transportation tool sensor data, transportation space environment data, and transportation scheduling route information of each same-space transportation tool of the current transportation tool to obtain the initial planned dynamic transportation scheduling route of each same-space transportation tool of the current transportation tool; Determine whether the initial planned dynamic transport scheduling route of the current transport tool intersects with the initial planned dynamic transport scheduling routes of all transport tools in the same space as the current transport tool. If so, treat all intersecting positions in the initial planned dynamic transport scheduling route of the current transport tool as all positions to be optimized, and treat the current transport tool and all transport tools in the same space where the corresponding initial planned dynamic transport scheduling routes intersect at each position to be optimized as candidate optimized transport tools for all transport scheduling routes at each position to be optimized; Based on the transport tool sensor data, transport space environment data, and transport scheduling route information of all transport scheduling route alternative optimization transport tools at each location to be optimized, calculate the first transport scheduling route optimizability degree of each transport scheduling route alternative optimization transport tool at the corresponding location to be optimized, wherein the first transport scheduling route optimizability degree refers to a quantitative value of the feasibility degree of preliminary transport scheduling route adjustment of a certain alternative optimization transport tool at the specific location to be optimized, as evaluated based on the transport tool sensor data, transport space environment data, and transport scheduling route information of all transport scheduling route alternative optimization transport tools at each location to be optimized; Based on the driving directions and driving speeds of all transport scheduling route alternative optimization transport tools at each location to be optimized, the degree of optimizability of the second transport scheduling route of each transport scheduling route alternative optimization transport tool at the location to be optimized is calculated: Where, OD R2 is the degree of optimizability of the second transport scheduling route of the currently calculated transport scheduling route alternative optimized transport tool at the currently calculated position to be optimized, v max The maximum speed that can be achieved by the alternative optimized transport vehicle for the currently calculated transport scheduling route, v h The speed of the alternative optimized transport vehicle for the currently calculated transport scheduling route at the currently calculated location to be optimized, C up The speed-up cost of the alternative transportation tool for the currently calculated transportation scheduling route is optimized, v min The minimum travel speed that can be achieved by the alternative optimized transport vehicle for the currently calculated transport scheduling route, C down is the deceleration cost of the alternative optimized transportation tool for the currently calculated transportation scheduling route, α1 is the driving speed optimization weight, a h1 If there are only two alternative transportation tools for the transportation scheduling route of the location to be optimized, the driving direction of the first alternative transportation tool for the transportation scheduling route is a, h2 If there are only two alternative transportation tools for the transportation scheduling route of the location to be optimized, the driving direction of the second alternative transportation tool for the transportation scheduling route is I(a h1 ,a h2 ) is the angle between the driving directions of the two alternative optimized transportation tools of the transportation scheduling route when there are only two alternative optimized transportation tools of the transportation scheduling route for the location to be optimized. α2 is the driving direction optimization weight. n is the total number of alternative optimized transportation tools of the transportation scheduling route for the location to be optimized. h0 Optimize the driving direction of the transport tool for the currently calculated transport scheduling route alternative, a hi The driving direction of the i-th transport scheduling route alternative optimization transport tool among all the transport scheduling route alternative optimization transport tools of the currently calculated position to be optimized, except the currently calculated transport scheduling route alternative optimization transport tool, and i = 3, 4, 5 ..., n, max[I(a h0 ,a hi )] is the maximum value of the angles between the driving direction of the currently calculated alternative optimized transport means for the transport scheduling route and the driving directions of all the currently calculated alternative optimized transport means for the transport scheduling route at the position to be optimized except the currently calculated alternative optimized transport means for the transport scheduling route; Calculate the transport scheduling route optimizability of all transport scheduling route alternative optimization transport tools at each location to be optimized based on the first transport scheduling route optimizability and the second transport scheduling route optimizability of each transport scheduling route alternative optimization transport tool at the location to be optimized; All transport scheduling route alternative optimization transport means, except the transport scheduling route alternative optimization transport means with the minimum transport scheduling route optimization degree, among all transport scheduling route alternative optimization transport means of each location to be optimized are regarded as the target transport scheduling route optimization transport means of each location to be optimized; Based on all positions to be optimized, the initial planned dynamic transportation scheduling route of the transportation tool corresponding to the target transportation scheduling route is optimized to avoid the transportation scheduling route, and the final planned dynamic transportation scheduling route of the current transportation tool is obtained as the transportation scheduling route scheduling strategy of the current transportation tool; Otherwise, generating a transportation scheduling route scheduling strategy for the current transportation tool based on the initial planned dynamic transportation scheduling route of the current transportation tool; S3: Generates the terminal freight hub scheduling strategy for the current transport tool based on the current cargo information, freight hub information, information on the coordination of transport tools in the same space, and the artificial intelligence big model; S4: The transportation scheduling route scheduling strategy of the current transportation tool and the terminal freight hub scheduling strategy are combined to obtain the transportation scheduling strategy of the current transportation tool.

2. The intelligent scheduling method based on artificial intelligence large model according to claim 1 is characterized in that: S1: Collect current transport tool sensor data, transport space environment data, transport scheduling route information, cargo information, freight hub information, and information on collaboration with transport tools in the same space, including: Collecting the current position, current speed, current direction, and current state parameters of the current transport tool as current transport tool sensor data; Determine a current transport space environment monitoring area based on the current position of the current transport vehicle, and collect transport space environment data within the current transport space environment monitoring area; Collect the terminal location information of the current transportation tool, the freight hub information passed through, and the transportation scheduling route restriction conditions as the current transportation scheduling route information; Collect the type of cargo, cargo weight, and loading and unloading requirements of the current transport vehicle as current cargo information; Collect the capacity distribution information and loading and unloading equipment status information of all terminal freight hubs of the current transportation means as the current freight hub information; Based on high-frequency wireless communication, the collaborative information of all the same-space transportation tools of the current transportation tool is collected as the same-space transportation tool collaborative information.

3. The intelligent scheduling method based on artificial intelligence large model according to claim 1 is characterized in that: S3: Generates the terminal freight hub dispatch strategy for the current transport vehicle based on the current cargo information, freight hub information, information on the coordination of transport vehicles in the same space, and the artificial intelligence model, including: Build an intelligent model for matching and evaluating loading and unloading requirements; The cargo type and loading and unloading requirements in the current cargo information, as well as the loading and unloading equipment status information of each terminal freight hub of the current transportation vehicle, are input into the loading and unloading requirement matching evaluation intelligent model to obtain the current loading and unloading demand matching degree of each terminal freight hub; Among all the terminal freight hubs of the current transport means, all terminal freight hubs whose current loading and unloading demand matching degree is not less than the loading and unloading demand matching degree threshold are regarded as all the current alternative freight hubs; Based on current cargo information, current freight hub information, information on the coordination of transport vehicles in the same space, transport scheduling route scheduling strategies and artificial intelligence big models, the predicted busyness of each candidate freight hub is determined; The freight hub with the lowest predicted busyness among all the current alternative freight hubs is selected as the target arrival freight hub; Generate a destination freight hub scheduling strategy based on the target arrival freight hub.

4. The intelligent scheduling method based on artificial intelligence large model according to claim 3 is characterized in that: Based on current cargo information, current freight hub information, information on co-location transport tools, transport routing strategies, and artificial intelligence models, the predicted busyness of each candidate freight hub is determined, including: Build an intelligent model for predicting freight hub busyness; The current cargo information, current freight hub information, information on the coordination of transport tools in the same space, and transport scheduling route scheduling strategies are input into the freight hub busyness prediction intelligent model to obtain the current predicted busyness of each alternative freight hub.

5. An intelligent scheduling system based on an artificial intelligence large model, characterized in that: The method for executing the intelligent scheduling method based on the artificial intelligence large model according to any one of claims 1 to 4 comprises: The information collection module is used to collect current transport tool sensor data, transport space environment data, transport scheduling route information, cargo information, freight hub information, and information on collaboration between transport tools in the same space; The transport scheduling route scheduling module is used to generate the transport scheduling route scheduling strategy of the current transport tool based on the current transport tool sensor data, transport space environment data, transport scheduling route information, cargo information, co-space transport tool collaboration information and artificial intelligence large model; The freight hub scheduling module is used to generate the terminal freight hub scheduling strategy of the current transport tool based on the current cargo information, freight hub information, the coordination information of the same space transport tools and the artificial intelligence big model; The comprehensive scheduling module is used to combine the transportation scheduling route scheduling strategy of the current transportation tool and the terminal freight hub scheduling strategy to obtain the transportation scheduling strategy of the current transportation tool.

Images