Intelligent scheduling method and system based on artificial intelligence large model

Abstract

The invention relates to the technical field of scheduling management, and particularly discloses an intelligent scheduling method and system based on an artificial intelligence large model. The method comprises the following steps: generating a transportation scheduling route scheduling strategy of a current transportation tool based on current transportation tool sensing data, transportation space environment data, transportation scheduling route information, cargo information, co-space transportation tool cooperation information and an artificial intelligence large model; generating a terminal freight hub scheduling strategy of the current transportation tool based on the current cargo information, the freight hub information, the co-space transportation tool cooperation information and an artificial intelligence large model; merging the transportation scheduling route scheduling strategy of the current transportation tool and the terminal freight hub scheduling strategy to obtain a transportation scheduling strategy of the current transportation tool; the method and the device are used for optimizing transportation paths and freight hub selection of transportation tools, reducing transportation cost, 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 particularly relates to an intelligent scheduling method and system based on an artificial intelligence large model. Background Art

[0002] At present, in the current wave of digital and intelligent industrial development, industrial cloud computing, industrial cloud platforms, and industrial Internet platforms are gradually becoming the key forces driving industrial transformation and upgrading. With the continuous development of the manufacturing industry and the increasing closeness of global trade, enterprises have higher and higher requirements for production efficiency, quality control, and supply chain management. In the transportation field, the scheduling of transportation tools is a key link to ensure the safe, efficient, and economical operation of transportation. With the continuous growth of global trade, the scale and complexity of transportation are increasing day by day, and the requirements for the scheduling of transportation tools are also getting higher and higher. Traditional methods for scheduling transportation tools mainly rely on manual experience and limited data, and it is difficult to cope with the changing transportation space environment, complex transportation scheduling route planning, and diverse cargo and freight hub requirements. Nowadays, with the development of information technology, transportation tools are equipped with various advanced sensing devices, which can collect a large amount of transportation tool sensing data and transportation space environment data in real time. At the same time, transportation scheduling route information, cargo information, freight hub information, and collaborative information of transportation tools in the same space have become more abundant and accurate. In addition, in terms of production collaboration, transportation scheduling also needs to cooperate closely with many links. The scheduling of transportation tools needs to be coordinated with the production progress and storage capacity of the cargo to avoid cargo backlogs or idle transportation resources. At the same time, it is necessary to cooperate with the loading and unloading operations of the freight hub to optimize the time of transportation tools at the freight hub. Moreover, different transportation tools in the same space should also be efficiently coordinated to achieve the optimal allocation of resources and improve the operation efficiency of the entire transportation system. However, how to effectively integrate and analyze these massive multi-source heterogeneous data to generate scientific and reasonable scheduling strategies is still a huge challenge.

[0003] In current transportation scheduling, there is a lack of 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 coordination between information of different cloud platforms is insufficient, resulting in the integrity and adaptability of the scheduling plan being less than ideal, affecting the efficiency and safety of transportation. Existing scheduling methods are difficult to efficiently integrate complex data from multiple sources, affecting the comprehensiveness of scheduling strategies. When generating scheduling strategies, insufficient consideration is given to information such as the coordination of transportation tools in the same space, and thus the scheduling strategy cannot be adjusted in a timely manner according to real-time changes, resulting in insufficient timeliness of the strategy, ultimately affecting production scheduling and making it impossible to improve production efficiency. Especially during emergency scheduling, the emergency response ability cannot be further enhanced.

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

[0005] The present invention provides an intelligent scheduling method and system based on an artificial intelligence large model, which collects comprehensive information such as transportation tool sensing data and transportation space environment data, providing a rich data basis for generating accurate and effective scheduling strategies. Based on the artificial intelligence large model, a transportation scheduling route strategy for transportation tools is generated, which can make full use of the powerful computing and analysis capabilities of the large model to formulate a more scientific and reasonable transportation scheduling route plan. According to cargo information, freight hub information, etc., an end freight hub scheduling strategy is generated, improving the pertinence and efficiency of freight hub scheduling. The transportation scheduling route strategy and the end freight hub scheduling strategy are combined to form a complete transportation scheduling strategy, making the scheduling plan more comprehensive and ensuring the high efficiency and safety of the transportation tool's driving. This intelligent scheduling method can optimize the transportation path of transportation tools and the selection of freight hubs, reduce transportation costs, improve transportation efficiency, and enhance the reliability and competitiveness of transportation.

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

[0007] S1: Collect current transportation tool sensing data, transportation space environment data, transportation scheduling route information, cargo information, freight hub information, and co-space transportation tool collaboration information;

[0008] S2: Generate a transportation scheduling route strategy for the current transportation tool based on the current transportation tool sensing data, transportation space environment data, transportation scheduling route information, cargo information, co-space transportation tool collaboration information, and the artificial intelligence large model;

[0009] S3: Generate an end freight hub scheduling strategy for the current transportation tool based on the current cargo information, freight hub information, co-space transportation tool collaboration information, and the artificial intelligence large model;

[0010] S4: Combine the transportation scheduling route strategy and the end freight hub scheduling strategy of the current transportation tool to obtain the transportation scheduling strategy of the current transportation tool.

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

[0012] Collect the current position, current speed, current direction, and current transportation tool status parameters of the current transportation tool as the current transportation tool sensing data;

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

[0014] Collect the end position information of the current transportation vehicle, the information of the freight hubs along the way, and the transportation scheduling route restriction conditions as the current transportation scheduling route information;

[0015] Collect the types of goods loaded on the current transportation vehicle, the weight of the goods, and the loading and unloading requirements as the current goods information;

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

[0017] Collect the cooperation information of all transportation vehicles in the same space of the current transportation vehicle based on high-frequency wireless communication as the cooperation information of transportation vehicles in the same space.

[0018] Preferably, for the intelligent scheduling method based on the artificial intelligence large model, S2: Generate the transportation scheduling route scheduling strategy of the current transportation vehicle based on the current transportation vehicle sensing data, transportation space environment data, transportation scheduling route information, cooperation information of transportation vehicles in the same space, and the artificial intelligence large model, including:

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

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

[0021] Input the current transportation vehicle sensing data, transportation space environment data, and transportation scheduling route information into the intelligent model for transportation scheduling route planning to obtain the initial planned transportation scheduling route of the current transportation vehicle;

[0022] Obtain the initial planned transportation scheduling routes of all transportation vehicles in the same space of the current transportation vehicle based on the cooperation information of transportation vehicles in the same space;

[0023] Generate the transportation scheduling route scheduling strategy of the current transportation vehicle based on the initial planned transportation scheduling route of the current transportation vehicle and the initial planned transportation scheduling routes of all transportation vehicles in the same space of the current transportation vehicle.

[0024] Preferably, for the intelligent scheduling method based on the artificial intelligence large model, generate the transportation scheduling route scheduling strategy of the current transportation vehicle based on the initial planned transportation scheduling route of the current transportation vehicle and the initial planned transportation scheduling routes of all transportation vehicles in the same space of the current transportation vehicle, including:

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

[0026] Dynamically simulate the initial planned transportation scheduling route of each co - space transportation vehicle of the current transportation vehicle based on the transportation vehicle sensing data, transportation space environment data, and transportation scheduling route information of each co - space transportation vehicle of the current transportation vehicle to obtain the initial planned dynamic transportation scheduling route of each co - space transportation vehicle of the current transportation vehicle;

[0027] Determine whether there is an intersection between the initial planned dynamic transportation scheduling route of the current transportation vehicle and the initial planned dynamic transportation scheduling routes of all co - space transportation vehicles of the current transportation vehicle. If so, optimize the initial planned dynamic transportation scheduling route of the current transportation vehicle or the initial planned dynamic transportation scheduling routes of all co - space transportation vehicles of the current transportation vehicle to obtain the transportation scheduling route scheduling strategy of the current transportation vehicle. Otherwise, generate the transportation scheduling route scheduling strategy of the current transportation vehicle based on the initial planned dynamic transportation scheduling route of the current transportation vehicle.

[0028] Preferably, an intelligent scheduling method based on an artificial intelligence large - model is used to optimize the initial planned dynamic transportation scheduling route of the current transportation vehicle or the initial planned dynamic transportation scheduling routes of all co - space transportation vehicles of the current transportation vehicle to obtain the transportation scheduling route scheduling strategy of the current transportation vehicle, including:

[0029] Regard all intersection positions in the initial planned dynamic transportation scheduling route of the current transportation vehicle as all positions to be optimized, and regard the current transportation vehicle and all co - space transportation vehicles where the corresponding initial planned dynamic transportation route generates intersections at each position to be optimized as all alternative optimized transportation vehicles for the transportation scheduling route at each position to be optimized;

[0030] Based on the transportation vehicle sensing data, transportation space environment data, and transportation scheduling route information of all alternative optimized transportation vehicles for the transportation scheduling route at each position to be optimized, calculate the optimizability of the transportation scheduling routes of all alternative optimized transportation vehicles for the transportation scheduling route at the corresponding position to be optimized;

[0031] Regard all alternative optimized transportation vehicles for the transportation scheduling route at each position to be optimized except the alternative optimized transportation vehicle with the minimum optimizability of the transportation scheduling route as the target transportation scheduling route optimized transportation vehicle at each position to be optimized;

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

[0033] Preferably, for the intelligent scheduling method based on the large artificial intelligence model, based on the transportation vehicle sensing data, transportation space environment data, and transportation scheduling route information of all alternative optimized transportation vehicles for each position to be optimized, calculate the optimizability of the transportation scheduling route of all alternative optimized transportation vehicles for each position to be optimized at the corresponding position to be optimized, including:

[0034] Based on the transportation vehicle sensing data, transportation space environment data, and transportation scheduling route information of all alternative optimized transportation vehicles for each position to be optimized, calculate the optimizability of the first transportation scheduling route of each alternative optimized transportation vehicle for each position to be optimized at the corresponding position to be optimized;

[0035] Based on the driving direction and driving speed of all alternative optimized transportation vehicles for each position to be optimized at the corresponding position to be optimized, calculate the optimizability of the second transportation scheduling route of each alternative optimized transportation vehicle for each position to be optimized at the corresponding position to be optimized;

[0036] Based on the optimizability of the first transportation scheduling route and the optimizability of the second transportation scheduling route of each alternative optimized transportation vehicle for each position to be optimized at the corresponding position to be optimized, calculate the optimizability of the transportation scheduling route of all alternative optimized transportation vehicles for each position to be optimized at the corresponding position to be optimized.

[0037] Preferably, for the intelligent scheduling method based on the large artificial intelligence model, based on the driving direction and driving speed of all alternative optimized transportation vehicles for each position to be optimized at the corresponding position to be optimized, calculate the optimizability of the second transportation scheduling route of each alternative optimized transportation vehicle for each position to be optimized at the corresponding position to be optimized, including:

[0038]

[0039] In the formula, OD R2 is the optimizability of the second transportation scheduling route of the currently calculated alternative optimized transportation vehicle for the currently calculated position to be optimized at the corresponding position to be optimized, v max is the maximum driving speed that the currently calculated alternative optimized transportation vehicle can reach, v hThe driving speed of the alternative optimized transportation vehicle for the currently calculated transportation scheduling route at the position to be optimized in the current calculation, C up The acceleration cost of the alternative optimized transportation vehicle for the currently calculated transportation scheduling route, v min The minimum driving speed that the alternative optimized transportation vehicle for the currently calculated transportation scheduling route can reach, C down The deceleration cost of the alternative optimized transportation vehicle for the currently calculated transportation scheduling route, α1 is the driving speed optimization weight, a h1 The driving direction of the first alternative optimized transportation vehicle for the transportation scheduling route at the position to be optimized in the current calculation if there are only 2 alternative optimized transportation vehicles, a h2 The driving direction of the second alternative optimized transportation vehicle for the transportation scheduling route at the position to be optimized in the current calculation if there are only 2 alternative optimized transportation vehicles, I(a h1 ,a h2 ) is the included angle between the driving directions of the two corresponding alternative optimized transportation vehicles for the transportation scheduling route at the position to be optimized in the current calculation if there are only 2 alternative optimized transportation vehicles, α2 is the driving direction optimization weight, n is the total number of alternative optimized transportation vehicles for the transportation scheduling route at the position to be optimized in the current calculation, a h0 The driving direction of the alternative optimized transportation vehicle for the currently calculated transportation scheduling route, a hi The driving direction of the i-th alternative optimized transportation vehicle among all alternative optimized transportation vehicles for the transportation scheduling route at the position to be optimized in the current calculation except the currently calculated alternative optimized transportation vehicle, and i = 3, 4, 5…, n, max[I(a h0 ,a hi )] is the maximum value among the included angles between the driving direction of the currently calculated alternative optimized transportation vehicle and the driving directions of all alternative optimized transportation vehicles among all alternative optimized transportation vehicles for the transportation scheduling route at the position to be optimized in the current calculation except the currently calculated alternative optimized transportation vehicle.

[0040] Preferably, for the intelligent scheduling method based on the artificial intelligence large model, S3: Based on the current cargo information, freight hub information, same-space transportation vehicle collaboration information, and the artificial intelligence large model, generate the end freight hub scheduling strategy for the current transportation vehicle, including:

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

[0042] Input the cargo type and loading and unloading requirements in the current cargo information and the loading and unloading equipment status information of each end freight hub of the current transportation vehicle into the intelligent model for matching and evaluating loading and unloading requirements to obtain the current loading and unloading demand matching degree of each end freight hub.

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

[0044] Based on the current cargo information, current freight hub information, same-space means of transportation collaboration information, transportation scheduling route scheduling strategy, and the artificial intelligence large model, determine the predicted busyness of each current alternative freight hub;

[0045] Among all the current alternative freight hubs, the alternative freight hub with the minimum predicted busyness is used as the target arrival freight hub;

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

[0047] Preferably, for the intelligent scheduling method based on the artificial intelligence large model, based on the current cargo information, current freight hub information, same-space means of transportation collaboration information, transportation scheduling route scheduling strategy, and the artificial intelligence large model, determine the predicted busyness of each current alternative freight hub, including:

[0048] Build an intelligent model for predicting the busyness of freight hubs;

[0049] Input the current cargo information, current freight hub information, same-space means of transportation collaboration information, and transportation scheduling route scheduling strategy into the intelligent model for predicting the busyness of freight hubs to obtain the predicted busyness of each current alternative freight hub.

[0050] The present invention provides an intelligent scheduling system based on the artificial intelligence large model for executing any one of the above intelligent scheduling methods based on the artificial intelligence large model, including:

[0051] An information collection module for collecting the sensing data of the current means of transportation, transportation space environment data, transportation scheduling route information, cargo information, freight hub information, and same-space means of transportation collaboration information;

[0052] A transportation scheduling route scheduling module for generating a transportation scheduling route scheduling strategy for the current means of transportation based on the sensing data of the current means of transportation, transportation space environment data, transportation scheduling route information, cargo information, same-space means of transportation collaboration information, and the artificial intelligence large model;

[0053] A freight hub scheduling module for generating a terminal freight hub scheduling strategy for the current means of transportation based on the current cargo information, freight hub information, same-space means of transportation collaboration information, and the artificial intelligence large model;

[0054] The integrated scheduling module is used to merge the transportation scheduling route scheduling strategy and the terminal freight hub scheduling strategy of the current transportation vehicle to obtain the transportation scheduling strategy of the current transportation vehicle.

[0055] The beneficial effects of the present invention compared with the prior art are as follows: By collecting comprehensive information such as the sensing data of transportation vehicles and the transportation space environment data, it provides a rich data basis for generating accurate and effective scheduling strategies. Generating the transportation scheduling route scheduling strategy of transportation vehicles based on the large artificial intelligence model can make full use of the powerful computing and analysis capabilities of the large model to formulate a more scientific and reasonable transportation scheduling route plan. Generating the terminal freight hub scheduling strategy based on cargo information, freight hub information, etc. improves the pertinence and efficiency of freight hub scheduling. Merging the transportation scheduling route scheduling strategy and the terminal freight hub scheduling strategy to form a complete transportation scheduling strategy makes the scheduling plan more comprehensive and overall, ensuring the high efficiency and safety of the driving of transportation vehicles. This intelligent scheduling method can optimize the transportation path of transportation vehicles and the selection of freight hubs, reduce transportation costs, improve transportation efficiency, enhance the reliability and competitiveness of transportation, especially when emergency scheduling is required, it can further improve the emergency response ability.

[0056] Other features and advantages of the present invention will be described in the subsequent description, and some of them will become obvious from the description or be understood by implementing the present invention. The objectives 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 solutions of the present invention will be further described in detail below through the drawings and embodiments. Description of the Drawings

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

[0059] Figure 1 It is a flowchart of the intelligent scheduling method based on the large artificial intelligence model in the embodiment of the present invention;

[0060] Figure 2 It is an internal functional module diagram of the intelligent scheduling system based on the large artificial intelligence model in the embodiment of the present invention. Detailed Embodiments

[0061] The following describes the preferred embodiments of the present invention with reference to the 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] Embodiment 1:

[0063] The present invention provides an intelligent scheduling method based on an artificial intelligence large model, with reference to Figure 1 , including:

[0064] S1: Collect the current transportation vehicle sensing data, transportation space environment data, transportation scheduling route information, cargo information, freight hub information, and co-space transportation vehicle collaboration information;

[0065] S2: Generate a transportation scheduling route scheduling strategy for the current transportation vehicle based on the current transportation vehicle sensing data, transportation space environment data, transportation scheduling route information, cargo information, co-space transportation vehicle collaboration information, and the artificial intelligence large model;

[0066] S3: Generate an end freight hub scheduling strategy for the current transportation vehicle based on the current cargo information, freight hub information, co-space transportation vehicle collaboration information, and the artificial intelligence large model;

[0067] S4: Combine the transportation scheduling route scheduling strategy and the end freight hub scheduling strategy of the current transportation vehicle to obtain the transportation scheduling strategy of the current transportation vehicle.

[0068] In this embodiment, the artificial intelligence large model: is a complex intelligent model with powerful computing and analysis capabilities, capable of processing and integrating a large amount of transportation vehicle-related data to provide support for generating scheduling strategies.

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

[0070] In this embodiment, the end freight hub scheduling strategy of the current transportation vehicle: is a strategy for determining the final freight hub to which the current transportation vehicle docks based on cargo, freight hub, and collaboration information, etc., including arrangements such as which freight hub to select as the final destination and the arrival time, etc.

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

[0072] The beneficial effects of the above technology are as follows: By collecting comprehensive information such as transportation vehicle sensor data and transportation space environment data, it provides a rich data foundation for generating accurate and effective scheduling strategies. Based on the artificial intelligence large model to generate the transportation scheduling route strategy of transportation vehicles, it can make full use of the powerful computing and analysis capabilities of the large model to formulate a more scientific and reasonable transportation scheduling route plan. Generate the terminal freight hub scheduling strategy based on cargo information, freight hub information, etc., improving the pertinence and efficiency of freight hub scheduling. Combine the transportation scheduling route strategy and the terminal freight hub scheduling strategy to form a complete transportation scheduling strategy, making the scheduling plan more comprehensive and ensuring the efficiency and safety of the transportation vehicle's travel. This intelligent scheduling method can optimize the transportation path of transportation vehicles and the selection of freight hubs, reduce transportation costs, improve transportation efficiency, and enhance the reliability and competitiveness of transportation.

[0073] Embodiment 2:

[0074] Based on the intelligent scheduling method of the artificial intelligence large model on the basis of Embodiment 1, S1: Collect the current transportation vehicle sensor data, transportation space environment data, transportation scheduling route information, cargo information, freight hub information, and co-space transportation vehicle collaboration information, including:

[0075] Collect the current position, current speed, current direction, and current transportation vehicle status parameters of the current transportation vehicle as the current transportation vehicle sensor data;

[0076] Based on the current position of the current transportation vehicle, determine the current transportation space environment monitoring area, and collect the altitude distribution data, wind direction and speed distribution data, vehicle flow speed and direction distribution data within the current transportation space environment monitoring area as the current transportation space environment data;

[0077] Collect the terminal position information, passing freight hub information, and transportation scheduling route restriction conditions of the current transportation vehicle as the current transportation scheduling route information;

[0078] Collect the cargo type, cargo weight, and loading and unloading requirements loaded on the current transportation vehicle as the 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 vehicle as the current freight hub information;

[0080] Collect the collaboration information of all co-space transportation vehicles of the current transportation vehicle based on high-frequency wireless communication as the co-space transportation vehicle collaboration information.

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

[0082] In this embodiment, the current speed: is the instantaneous speed at which the current means of transportation is traveling.

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

[0084] In this embodiment, the current state parameters of the means of transportation: include parameters such as the operating condition of the equipment of the means of transportation, the remaining fuel, and the structural integrity of the means of transportation, which describe the condition of the means of transportation itself.

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

[0086] In this embodiment, determining the current transportation space environment monitoring area based on the current position of the current means of transportation: demarcates a specific range that needs to monitor the transportation space environment according to the specific position where the current means of transportation is located.

[0087] In this embodiment, the altitude distribution data, wind direction and speed distribution data, traffic flow speed and direction distribution data within the current transportation space environment monitoring area: are data obtained by measuring and recording the changes in altitude at different positions, the changes in wind direction and speed at different positions, and the changes in traffic flow speed and direction at different positions in the demarcated current transportation space environment monitoring area.

[0088] In this embodiment, the end position information of the current means of transportation, the information of the freight hubs along the way, and the transportation scheduling route restriction conditions:

[0089] The end position information refers to the final destination that the means of transportation plans to reach in this trip;

[0090] The information of the freight hubs along the way is the relevant information of the freight hubs that the means of transportation plans to stop at during the process of reaching the end;

[0091] The transportation scheduling route restriction conditions include conditions such as road width, waterway depth, bridge height, and tunnel height that may restrict the driving route of the means of transportation.

[0092] In this embodiment, the types of goods loaded on the current means of transportation, the weight of the goods, and the loading and unloading requirements:

[0093] The types of goods are the categories of the goods loaded on the ship;

[0094] The weight of the goods is the total weight of the goods on the ship;

[0095] The loading and unloading requirements include the time, method, and equipment requirements for loading and unloading the goods.

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

[0097] The capacity distribution information refers to the distribution within the freight hub of the number of means of transportation that each terminal freight hub can accommodate, the cargo storage capacity, etc.

[0098] The loading and unloading equipment status information includes whether the loading and unloading equipment such as cranes and conveyor belts in the freight hub is operating normally, the working efficiency, etc.

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

[0100] In this embodiment, the collaborative information: refers to the information that the same-space means of transportation communicate and share with each other for the purposes of avoiding collisions, jams, optimizing the transportation scheduling route, etc., such as driving plans, positions, speeds, etc.

[0101] The beneficial effects of the above technologies include: detailed collection of sensing data such as the position, speed, direction, and status parameters of the current means of transportation, enabling a comprehensive understanding of the real-time condition of the means of transportation itself and providing a basis for precise scheduling. Determining the transportation space environment monitoring area based on the position of the means of transportation and collecting relevant data such as altitude, wind direction and speed, and traffic flow, which helps to fully consider the impact of the transportation space environment on the driving of the means of transportation. Collecting transportation scheduling route information including the terminal position, passing freight hubs, and transportation scheduling route restriction conditions, making the transportation scheduling route planning more in line with actual needs and restrictions. Carefully collecting cargo information such as the type, weight, and loading and unloading requirements of the cargo, which is beneficial to reasonably arranging the loading and unloading plan and the transportation process. Obtaining freight hub information such as the capacity distribution and loading and unloading equipment status of the freight hub can improve the efficiency and rationality of freight hub scheduling. Collecting the collaborative information of the same-space means of transportation through high-frequency wireless communication enhances the collaboration and safety between the means of transportation. This comprehensive, detailed, and accurate data collection method provides rich, reliable, and precise data support for intelligent scheduling based on the artificial intelligence large model, helping to improve the scientificity, efficiency, and safety of scheduling.

[0102] Embodiment 3:

[0103] On the basis of Embodiment 1, for the intelligent scheduling method based on the artificial intelligence large model, S2: Generate a transportation scheduling route scheduling strategy for the current means of transportation based on the current means of transportation sensing data, transportation space environment data, transportation scheduling route information, same-space means of transportation collaborative information, and the artificial intelligence large model, including:

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

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

[0106] Input the current transportation vehicle sensing data, transportation space environment data, and transportation scheduling route information into the intelligent model for transportation scheduling route planning to obtain the initial planned transportation scheduling route of the current transportation vehicle;

[0107] Based on the collaborative information of the same-space transportation vehicles, obtain the initial planned transportation scheduling routes of all the same-space transportation vehicles of the current transportation vehicle;

[0108] Generate a transportation scheduling route scheduling strategy for the current transportation vehicle based on the initial planned transportation scheduling route of the current transportation vehicle and the initial planned transportation scheduling routes of all the same-space transportation vehicles of the current transportation vehicle.

[0109] In this embodiment, the terminal freight hub group: refers to a group of freight hubs with the final destination in a similar area.

[0110] In this embodiment, the minimum scheduling boundary position information: is the relevant information about the outermost position of the scope covered by the terminal freight hub group, and is used for planning transportation scheduling routes and scheduling decisions.

[0111] In this embodiment, build an intelligent model for transportation scheduling route planning: create an intelligent algorithm or system that can plan the transportation scheduling route of a transportation vehicle according to various input data and conditions. Usually, the following steps and training samples are required to build the intelligent model for transportation scheduling route planning:

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

[0113] Feature engineering: Extract meaningful features from the collected data, such as features of the transportation vehicle's position, speed, and direction, features of the transportation space environment, and features of the starting point, ending point, and passing points of the transportation scheduling route.

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

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

[0116] Training samples: Include the driving data of transportation vehicles under various different conditions, such as transportation vehicle sensing data, transportation space environment data, and actual transportation scheduling route information under different seasons, different weather conditions, different cargo types and weights, etc.

[0117] Include driving samples of different types and scales of transportation tools to meet the transportation scheduling route planning requirements of various transportation tools.

[0118] Cover combinations of various freight hubs and transportation scheduling routes, including situations such as busy freight hubs and unpopular transportation scheduling routes.

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

[0120] In this embodiment, the initial planned transportation scheduling route of the current transportation tool: the driving route preliminarily designed for the current transportation tool based on the initial conditions and data.

[0121] In this embodiment, based on the collaborative information of co-space transportation tools, obtain the initial planned transportation scheduling routes of all co-space transportation tools of the current transportation tool: utilize the collaborative information exchanged and shared among other co-space transportation tools to obtain the driving routes preliminarily set by these transportation tools, mainly by inputting the transportation tool sensing data, transportation space environment data, and transportation scheduling route information of each co-space transportation tool included in the co-space transportation tool collaborative information into the transportation scheduling route planning intelligent model.

[0122] The beneficial effects of the above technologies are as follows: Determine the minimum scheduling boundary position information of the terminal freight hub group based on the end position information, providing a clear scope and limit for transportation scheduling route planning and improving the accuracy of planning. Build a transportation scheduling route planning intelligent model, which can utilize the intelligent algorithms and learning ability of the model to generate more optimized transportation scheduling routes. Input various data into the model to obtain the initial planned transportation scheduling route, fully considering various factors such as the state of the transportation tool itself, the transportation space environment, and the requirements of the transportation scheduling route. Obtain the initial planned transportation scheduling routes of other transportation tools based on the collaborative information of co-space transportation tools, which helps to avoid transportation scheduling route conflicts and improve the safety and efficiency of space driving. Generate a transportation scheduling route scheduling strategy by comprehensively considering the initial planned transportation scheduling routes of the current transportation tool and co-space transportation tools, making the scheduling strategy more comprehensive, reasonable, and coordinated. This method can effectively plan a safe, efficient, and coordinated transportation tool transportation scheduling route scheduling strategy, improve the efficiency and safety of transportation, and reduce driving risks and costs.

[0123] Embodiment 4:

[0124] Based on the intelligent scheduling method of the artificial intelligence large model on the basis of Embodiment 3, generate the transportation scheduling route scheduling strategy 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 co-space transportation tools of the current transportation tool, including:

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

[0126] Dynamically simulate the initial planned transportation scheduling route of each co - space transportation vehicle of the current transportation vehicle based on the transportation vehicle sensing data, transportation space environment data, and transportation scheduling route information of each co - space transportation vehicle of the current transportation vehicle to obtain the initial planned dynamic transportation scheduling route of each co - space transportation vehicle of the current transportation vehicle;

[0127] Determine whether there is an intersection between the initial planned dynamic transportation scheduling route of the current transportation vehicle and the initial planned dynamic transportation scheduling routes of all co - space transportation vehicles of the current transportation vehicle. If so, optimize the initial planned dynamic transportation scheduling route of the current transportation vehicle or the initial planned dynamic transportation scheduling routes of all co - space transportation vehicles of the current transportation vehicle to obtain the transportation scheduling route scheduling strategy of the current transportation vehicle. Otherwise, generate the transportation scheduling route scheduling strategy of the current transportation vehicle based on the initial planned dynamic transportation scheduling route of the current transportation vehicle.

[0128] In this embodiment, the initial planned transportation scheduling route of the current transportation vehicle is dynamically simulated based on the current transportation vehicle sensing data, transportation space environment data, and transportation scheduling route information to obtain the initial planned dynamic transportation scheduling route of the current transportation vehicle: Input the data collected by the sensors of the current transportation vehicle, the relevant data of the transportation space environment where it is located, and the initial planned transportation scheduling route information into the simulation system. By considering various dynamic change factors in actual driving, such as transportation vehicle speed, transportation space environment changes, etc., the transportation vehicle driving route closer to the actual situation is obtained, that is, the initial planned dynamic transportation scheduling route.

[0129] In this embodiment, the initial planned transportation scheduling route of each co - space transportation vehicle of the current transportation vehicle is dynamically simulated based on the transportation vehicle sensing data, transportation space environment data, and transportation scheduling route information of each co - space transportation vehicle of the current transportation vehicle to obtain the initial planned dynamic transportation scheduling route of each co - space transportation vehicle of the current transportation vehicle: For each transportation vehicle in the co - space, similar dynamic simulations are carried out according to its own sensor data, the transportation space environment conditions where it is located, and the initial planned transportation scheduling route, so as to obtain their respective initial planned dynamic transportation scheduling routes.

[0130] In this embodiment, the transportation scheduling route scheduling strategy of the current transportation vehicle is generated based on the initial planned dynamic transportation scheduling route of the current transportation vehicle: The final transportation scheduling route arrangement decision is made according to the initial planned dynamic transportation scheduling route of the current transportation vehicle, that is, the transportation scheduling route scheduling strategy.

[0131] The beneficial effects of the above technology are as follows: By dynamically simulating the initially planned transportation scheduling route of the current transportation vehicle, it can more realistically predict the transportation scheduling route situation and take into account the influence of various dynamic factors. It also dynamically simulates the initially planned transportation scheduling route of the transportation vehicles in the same space, comprehensively grasping the dynamic situation of the transportation scheduling routes in the space. By judging whether there are intersections in the initially planned dynamic transportation scheduling route, potential conflicts and risks can be discovered in a timely manner. Optimize the dynamic transportation scheduling routes with intersections, effectively avoiding conflicts in transportation scheduling routes and improving the safety and efficiency of driving. The generated transportation scheduling route scheduling strategy fully considers the dynamic situation and the relationship between transportation vehicles, making the scheduling more reasonable and reliable. This way of generating the transportation scheduling route scheduling strategy through dynamic simulation and optimization can significantly enhance the orderliness and safety of traffic, reduce the accident rate, and improve transportation efficiency and economic benefits.

[0132] Example 5:

[0133] Based on the intelligent scheduling method of the artificial intelligence large model on the basis of Example 4, optimize the initially planned dynamic transportation scheduling route of the current transportation vehicle or the initially planned dynamic transportation scheduling routes of all transportation vehicles in the same space as the current transportation vehicle to obtain the transportation scheduling route scheduling strategy of the current transportation vehicle, including:

[0134] Regard all intersection positions in the initially planned dynamic transportation scheduling route of the current transportation vehicle as all positions to be optimized, and regard the current transportation vehicle and all transportation vehicles in the same space that generate intersections at each position to be optimized in the corresponding initially planned dynamic transportation scheduling route as all alternative optimized transportation vehicles for transportation scheduling routes at each position to be optimized;

[0135] Based on the transportation vehicle sensing data, transportation space environment data, and transportation scheduling route information of all alternative optimized transportation vehicles for transportation scheduling routes at each position to be optimized, calculate the optimizability of the transportation scheduling routes of all alternative optimized transportation vehicles for transportation scheduling routes at the corresponding position to be optimized;

[0136] Regard all alternative optimized transportation vehicles for transportation scheduling routes at each position to be optimized except the alternative optimized transportation vehicle for the transportation scheduling route with the minimum optimizability of the transportation scheduling route as the target optimized transportation vehicle for the transportation scheduling route at each position to be optimized;

[0137] Based on all positions to be optimized, perform transportation scheduling route avoidance optimization on the initially planned dynamic transportation scheduling routes of the corresponding target optimized transportation vehicles for transportation scheduling routes to obtain the finally planned dynamic transportation scheduling route of the current transportation vehicle as the transportation scheduling route scheduling strategy of the current transportation vehicle.

[0138] In this embodiment, the optimizability of the transportation scheduling routes of all alternative optimized transportation tools at each position to be optimized: refers to the feasibility and profitability of changing the transportation scheduling route at each position where there may be intersections of transportation scheduling routes that need to be optimized. For all transportation tools that can be selected for optimization, considering various factors such as the sensing data of the transportation tools, the transportation space environment data, and the transportation scheduling route information, the degree of feasibility and profitability of changing the transportation scheduling route at this position is evaluated.

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

[0140] The beneficial effects of the above technology are as follows: Regarding the intersection position as the position to be optimized and determining the relevant transportation tools as the alternative optimized transportation tools for the transportation scheduling route can accurately locate the areas and objects that need to be adjusted. Calculating the optimizability of the transportation scheduling routes of the alternative optimized transportation tools at each position to be optimized provides a quantitative basis for the optimization decision. Selecting the transportation tools other than the minimum optimizability of the transportation scheduling routes as the target transportation scheduling route optimized transportation tools makes the optimization more targeted and reasonable. Based on all positions to be optimized, the transportation scheduling route avoidance optimization is performed on the target transportation scheduling route optimized transportation tool, which can comprehensively solve the problem of transportation scheduling route conflicts and ensure safe and efficient driving. The finally obtained final planned dynamic transportation scheduling route of the current transportation tool as the transportation scheduling route scheduling strategy 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 at the same time reduce energy consumption and transportation costs.

[0141] Embodiment 6:

[0142] Based on the intelligent scheduling method of the artificial intelligence large model, on the basis of Embodiment 5, based on the sensing data of the transportation tools, the transportation space environment data, and the transportation scheduling route information of all alternative optimized transportation tools at each position to be optimized, calculate the optimizability of the transportation scheduling routes of all alternative optimized transportation tools at each position to be optimized, including:

[0143] Based on the transport vehicle sensing data, transport space environment data, and transport scheduling route information of all alternative optimized transport vehicles for each position to be optimized, calculate the first transport scheduling route optimizability of each alternative optimized transport vehicle for each position to be optimized at the corresponding position to be optimized;

[0144] Based on the driving directions and driving speeds of all alternative optimized transport vehicles for each position to be optimized at the corresponding position to be optimized, calculate the second transport scheduling route optimizability of each alternative optimized transport vehicle for each position to be optimized at the corresponding position to be optimized;

[0145] Based on the first transport scheduling route optimizability and the second transport scheduling route optimizability of each alternative optimized transport vehicle for each position to be optimized at the corresponding position to be optimized, calculate the transport scheduling route optimizability of all alternative optimized transport vehicles for each position to be optimized at the corresponding position to be optimized.

[0146] In this embodiment, based on the transport vehicle sensing data, transport space environment data, and transport scheduling route information of all alternative optimized transport vehicles for each position to be optimized, calculate the first transport scheduling route optimizability of each alternative optimized transport vehicle for each position to be optimized at the corresponding position to be optimized: at each position where the transport scheduling route needs to be optimized, for each transport vehicle that can be used as an adjustment object, comprehensively consider its own sensing data (such as the state of the transport vehicle), the situation of the transport space environment it is in, and the original transport scheduling route plan and other information to evaluate the preliminary feasibility of adjusting the transport scheduling route of this transport vehicle at this position.

[0147] In this embodiment, the first transport scheduling route optimizability of each alternative optimized transport vehicle for each position to be optimized at the corresponding position to be optimized: refers to the quantitative value of the preliminary feasibility of adjusting the transport scheduling route evaluated by a certain alternative optimized transport vehicle based on the above-mentioned partial data and information at a specific position to be optimized.

[0148] In this embodiment, the second transport scheduling route optimizability of each alternative optimized transport vehicle for each position to be optimized at the corresponding position to be optimized: at each position to be optimized, for each alternative optimized transport vehicle, it is another quantitative value of the feasibility of adjusting the transport scheduling route evaluated by further considering factors such as its driving direction and driving speed.

[0149] In this embodiment, based on the first transport scheduling route optimizability degree and the second transport scheduling route optimizability degree of each alternative optimized transport vehicle for the transport scheduling route at each position to be optimized, the transport scheduling route optimizability degree of all alternative optimized transport vehicles for the transport scheduling route at each position to be optimized is calculated: By comprehensively considering the quantization values of the above two transport scheduling route optimizability degrees of each transport vehicle at each position to be optimized, through a specific calculation method (such as taking the average of the two) or weight assignment, a comprehensive quantization value of the feasibility of adjusting the transport scheduling route for all alternative optimized transport vehicles at this position is obtained.

[0150] The beneficial effects of the above technologies include: Calculating the first transport scheduling route optimizability degree of each alternative optimized transport vehicle for the transport scheduling route at each position to be optimized based on multiple data, comprehensively considering various factors such as the transport vehicle itself and the environment, making the optimization evaluation more comprehensive. Calculating the second transport scheduling route optimizability degree based on the driving direction and speed, further evaluating the possibility and difficulty of optimization from a dynamic perspective. Calculating the final transport scheduling route optimizability degree by integrating the first and second transport scheduling route optimizability degrees, making the evaluation result more accurate and comprehensive. This multi-dimensional and detailed calculation method can more accurately determine the potential and difficulty of adjusting the transport scheduling route of each transport vehicle at the position to be optimized. It helps to formulate a more scientific and reasonable transport scheduling route optimization plan, minimize transport scheduling route conflicts to the greatest extent, and improve the efficiency and safety of transport scheduling route scheduling. It provides a reliable quantization basis and technical support for generating an efficient, safe and highly adaptable transport scheduling route scheduling strategy.

[0151] Embodiment 7:

[0152] Based on the intelligent scheduling method of the artificial intelligence large model on the basis of Embodiment 6, based on the driving direction and driving speed of all alternative optimized transport vehicles for the transport scheduling route at each position to be optimized, the second transport scheduling route optimizability degree of each alternative optimized transport vehicle for the transport scheduling route at each position to be optimized is calculated, including:

[0153]

[0154] In the formula, OD R2 is the second transport scheduling route optimizability degree of the currently calculated alternative optimized transport vehicle for the transport scheduling route at the currently calculated position to be optimized, v max is the maximum driving speed that the currently calculated alternative optimized transport vehicle can reach, v h is the driving speed of the currently calculated alternative optimized transport vehicle at the currently calculated position to be optimized, Cup The speed-up cost of the alternative optimized transportation vehicle for the currently calculated transportation scheduling route is v min The minimum driving speed that the alternative optimized transportation vehicle for the currently calculated transportation scheduling route can reach is C down The deceleration cost of the alternative optimized transportation vehicle for the currently calculated transportation scheduling route is α1, and the speed optimization weight is a h1 If there are only 2 alternative optimized transportation vehicles for the transportation scheduling route at the currently calculated position to be optimized, a is the driving direction of the first alternative optimized transportation vehicle among them h2 If there are only 2 alternative optimized transportation vehicles for the transportation scheduling route at the currently calculated position to be optimized, a is the driving direction of the second alternative optimized transportation vehicle among them, and I(a h1 , a h2 ) is the included angle between the driving directions of the two corresponding alternative optimized transportation vehicles if there are only 2 alternative optimized transportation vehicles for the transportation scheduling route at the currently calculated position to be optimized. α2 is the driving direction optimization weight, and n is the total number of alternative optimized transportation vehicles for the transportation scheduling route at the currently calculated position to be optimized, a h0 The driving direction of the alternative optimized transportation vehicle for the currently calculated transportation scheduling route is a hi a is the driving direction of the i-th alternative optimized transportation vehicle among all alternative optimized transportation vehicles for the transportation scheduling route at the currently calculated position to be optimized except the currently calculated alternative optimized transportation vehicle, and i = 3, 4, 5…, n. max[I(a h0 , a hi )] is the maximum value among the included angles between the driving direction of the currently calculated alternative optimized transportation vehicle and the driving directions of all alternative optimized transportation vehicles except the currently calculated alternative optimized transportation vehicle among all alternative optimized transportation vehicles for the transportation scheduling route at the currently calculated position to be optimized

[0155] In this embodiment, the maximum (minimum) driving speed that the currently calculated alternative optimized transportation vehicle can reach: refers to the upper (lower) limit of the highest (lowest) driving speed that this alternative optimized transportation vehicle can reach during the current analysis and calculation

[0156] In this embodiment, the speed-up (deceleration) cost of the currently calculated alternative optimized transportation vehicle: is the cost that this alternative optimized transportation vehicle needs to pay to increase (decrease) the driving speed, which may include costs in aspects such as energy consumption and mechanical wear

[0157] In this embodiment, the speed optimization weight: is the numerical value of the relative importance given to the factor of driving speed when calculating the optimizable degree of the transportation scheduling route

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

[0159] In this embodiment, the travel direction optimization weight: the value of the relative importance given to the factor of travel direction when calculating the optimizability of the transportation scheduling route.

[0160] The beneficial effects of the above technologies are as follows: By calculating the optimizability of the second transportation scheduling route through a clear mathematical formula, the influence of travel speed and travel direction on the optimization of the transportation scheduling route can be accurately quantified. Considering factors such as the maximum travel speed, minimum travel speed, acceleration cost, and deceleration cost of transportation tools makes the optimization evaluation in terms of speed more comprehensive and practical. Introducing the travel speed optimization weight and travel direction optimization weight can flexibly adjust the importance of speed and direction in the calculation of the optimization degree. For the calculation of the travel direction, the included angles between multiple transportation tools are comprehensively considered, accurately reflecting the role of the direction factor in the optimization of the transportation scheduling route. This accurate and comprehensive calculation method can provide a scientific and accurate basis for the optimization of the transportation scheduling route, helping to formulate a more reasonable and efficient transportation scheduling route scheduling strategy. It improves the accuracy and effect of the optimization of the transportation scheduling route, enhances the safety and efficiency of travel, and reduces the risk of conflicts in the transportation scheduling route.

[0161] Embodiment 8:

[0162] Based on the intelligent scheduling method of the artificial intelligence large model on the basis of Embodiment 1, S3: Based on the current cargo information, freight hub information, co-space transportation tool collaboration information, and artificial intelligence large model, generate the end freight hub scheduling strategy of the current transportation tool, including:

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

[0164] Input the cargo type and loading and unloading requirements in the current cargo information and the loading and unloading equipment status information of each end freight hub of the current transportation tool into the intelligent model for matching and evaluating loading and unloading requirements to obtain the current loading and unloading demand matching degree of each end freight hub;

[0165] Among all the end freight hubs of the current transportation tool, all the end freight hubs with the current loading and unloading demand matching degree not less than the loading and unloading demand matching degree threshold are regarded as all the current alternative freight hubs;

[0166] Based on the current cargo information, current freight hub information, co-space transportation tool collaboration information, transportation scheduling route scheduling strategy, and artificial intelligence large model, determine the predicted busyness of each current alternative freight hub;

[0167] Among all the current alternative freight hubs, select the alternative freight hub with the lowest predicted busyness as the target arrival freight hub;

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

[0169] In this embodiment, an intelligent model for evaluating the matching of handling requirements is established: Create an intelligent model that can evaluate the matching degree between the handling requirements of goods and the handling capacity of the freight hub according to information such as the type of goods, handling requirements, and the status of the handling equipment at the freight hub. Technologies such as neural networks can be used to establish the intelligent model for evaluating the matching of handling requirements. The training samples should contain rich and diverse information. First, there should be data on the detailed types, weights, and special handling requirements of various types of goods. Second, it should cover information such as the types, quantities, performance, and maintenance status of the handling equipment at different freight hubs. At the same time, historical handling operation data of the freight hub under different time periods (such as holidays, peak seasons, and off-seasons) and different weather conditions need to be included. It should also include records of the actual matching effects of different combinations of goods and handling equipment at different freight hubs, as well as data on the impact of the personnel configuration and work processes at the freight hub on handling, so that the model can accurately evaluate the matching degree.

[0170] In this embodiment, the current matching degree of handling requirements for each terminal freight hub: For each freight hub serving as the driving destination, a quantitative value that measures the degree to which conditions such as the status of its handling equipment meet the handling requirements of the goods of the current transportation vehicle.

[0171] In this embodiment, the threshold value of the matching degree of handling requirements: A preset standard value used to judge whether the matching degree of the handling requirements of the terminal freight hub is qualified.

[0172] In this embodiment, the predicted busyness of each current alternative freight hub: For each currently listed alternative freight hub, a quantitative estimated value of its future work busyness predicted through a model or algorithm.

[0173] In this embodiment, the target arrival freight hub: Among all alternative freight hubs, the freight hub selected as the final docking destination of the transportation vehicle according to factors such as predicted busyness.

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

[0175] The beneficial effects of the above technology are as follows: An intelligent model for evaluating the matching of loading and unloading requirements is built, which can accurately evaluate the matching degree between the loading and unloading requirements of goods and the status of loading and unloading equipment in the freight hub by using intelligent algorithms. The matching degree of loading and unloading requirements for each terminal freight hub is obtained through the model, providing a quantitative basis for selecting a suitable freight hub. The terminal freight hubs with a loading and unloading requirement matching degree not less than the threshold are screened out as alternative freight hubs, improving the accuracy and reliability of freight hub selection. The predicted busyness of each alternative freight hub is determined based on multiple pieces of information, fully considering various factors affecting the operation efficiency of the freight hub. Selecting the alternative freight hub with the minimum predicted busyness as the target arrival freight hub can minimize the waiting time to the greatest extent and improve the transportation efficiency. A scheduling strategy for the terminal freight hub is generated based on the target arrival freight hub, making the scheduling strategy more targeted and optimized. This method can achieve efficient and accurate scheduling of the terminal freight hub, reduce transportation costs, and improve the timeliness of goods transportation and the utilization rate of freight hub resources.

[0176] Embodiment 9:

[0177] Based on the intelligent scheduling method of the large artificial intelligence model in Embodiment 8, based on the current goods information, current freight hub information, co-space transportation tool collaboration information, transportation scheduling route scheduling strategy, and the large artificial intelligence model, the predicted busyness of each current alternative freight hub is determined, including:

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

[0179] Input the current goods information, current freight hub information, co-space transportation tool collaboration information, and transportation scheduling route scheduling strategy into the intelligent model for predicting the busyness of the freight hub to obtain the predicted busyness of each current alternative freight hub.

[0180] In this embodiment, building an intelligent model for predicting the busyness of the freight hub means creating an intelligent algorithm or system that can predict the future busyness of the freight hub based on the input current goods information, freight hub information, co-space transportation tool collaboration information, transportation scheduling route scheduling strategy, etc. Deep learning technology can be used to build the intelligent model for predicting the busyness of the freight hub. During the training process, the input quantities of the model include the historical cargo flow of the freight hub, types of goods, time and quantity of transportation tools entering and leaving the freight hub, status of freight hub equipment, weather conditions, co-space transportation tool collaboration information, current transportation scheduling route scheduling strategy, etc. The output quantity of the model is the predicted value of the busyness of the freight hub in the future for a period of time, which may be presented in the form of specific busyness values or busyness levels, etc., so as to provide a decision-making basis for freight hub scheduling.

[0181] The beneficial effects of the above technology are as follows: By building an intelligent model for predicting the busyness of freight hubs, it is possible to use a dedicated model for busyness prediction, improving the professionalism and accuracy of the prediction. By inputting various relevant information into the model, comprehensive factors such as goods, freight hubs, the coordination of transportation tools in the same space, and the transportation scheduling route scheduling strategy are fully considered, making the prediction results more comprehensive and reliable. The predicted busyness of each alternative freight hub is obtained through the model, providing accurate data support for selecting the optimal target arrival freight hub. This prediction method based on comprehensive information and intelligent models helps improve the efficiency and rationality of freight hub scheduling, reduce freight hub congestion and waiting time. It can better plan the selection of the terminal freight hub for transportation tools, enhancing the overall efficiency and economic benefits of goods transportation.

[0182] Embodiment 10:

[0183] The present invention provides an intelligent scheduling system based on an artificial intelligence large model for implementing any one of the intelligent scheduling methods based on an artificial intelligence large model in Embodiments 1 to 9, with reference to Figure 2 , and includes:

[0184] An information collection module for collecting current transportation tool sensing data, transportation space environment data, transportation scheduling route information, goods information, freight hub information, and the coordination information of transportation tools in the same space;

[0185] A transportation scheduling route scheduling module for generating a transportation scheduling route scheduling strategy for the current transportation tool based on the current transportation tool sensing data, transportation space environment data, transportation scheduling route information, goods information, the coordination information of transportation tools in the same space, and the artificial intelligence large model;

[0186] A freight hub scheduling module for generating a terminal freight hub scheduling strategy for the current transportation tool based on the current goods information, freight hub information, the coordination information of transportation tools in the same space, and the artificial intelligence large model;

[0187] A comprehensive scheduling module for 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 of the current transportation tool.

[0188] The beneficial effects of the above technology are as follows: By collecting comprehensive information such as transportation vehicle sensing data and transportation space environment data, it provides a rich data basis for generating accurate and effective scheduling strategies. Based on the artificial intelligence large model to generate the transportation scheduling route strategy of transportation vehicles, it can make full use of the powerful computing and analysis capabilities of the large model to formulate a more scientific and reasonable transportation scheduling route plan. Generating the terminal freight hub scheduling strategy according to the cargo information, freight hub information, etc., improves the pertinence and efficiency of freight hub scheduling. Combining the transportation scheduling route strategy and the terminal freight hub scheduling strategy to form a complete transportation scheduling strategy makes the scheduling plan more comprehensive and overall, ensuring the high efficiency and safety of the transportation vehicle's driving. This intelligent scheduling method can optimize the transportation path of transportation vehicles and the selection of freight hubs, reduce transportation costs, improve transportation efficiency, and enhance the reliability and competitiveness of transportation.

[0189] Obviously, those skilled in the art can make various changes and modifications to the present invention without departing from the spirit and scope of the present invention. Thus, if these modifications and variations of the present invention fall within the scope of the claims of the present invention and their equivalent technologies, the present invention is also intended to include these changes and modifications.

Claims

1. An intelligent scheduling method based on an artificial intelligence large model, characterized in that, Including: S1: Collect current transportation vehicle sensing data, transportation space environment data, transportation scheduling route information, cargo information, freight hub information, and collaborative information of transportation vehicles in the same space; S2: Generate a transportation scheduling route strategy for the current transportation vehicle based on the current transportation vehicle sensing data, transportation space environment data, transportation scheduling route information, cargo information, collaborative information of transportation vehicles in the same space, and an artificial intelligence large model; S3: Generate an end freight hub scheduling strategy for the current transportation vehicle based on the current cargo information, freight hub information, collaborative information of transportation vehicles in the same space, and an artificial intelligence large model; S4: Combine the transportation scheduling route strategy and the end freight hub scheduling strategy of the current transportation vehicle to obtain the transportation scheduling strategy of the current transportation vehicle.

2. The intelligent scheduling method based on the artificial intelligence large model according to claim 1, wherein S1: Collect current transportation vehicle sensing data, transportation space environment data, transportation scheduling route information, cargo information, freight hub information, and collaborative information of transportation vehicles in the same space, including: Collect the current position, current speed, current direction, and current transportation vehicle status parameters of the current transportation vehicle as the current transportation vehicle sensing data; Determine the current transportation space environment monitoring area based on the current position of the current transportation vehicle, and collect the transportation space environment data within the current transportation space environment monitoring area; Collect the end position information, freight hubs along the way information, and transportation scheduling route restriction conditions of the current transportation vehicle as the current transportation scheduling route information; Collect the cargo types, cargo weights, and loading and unloading requirements loaded on the current transportation vehicle as the current cargo information; Collect the capacity distribution information and loading and unloading equipment status information of all end freight hubs of the current transportation vehicle as the current freight hub information; Collect the collaborative information of all transportation vehicles in the same space of the current transportation vehicle as the collaborative information of transportation vehicles in the same space based on high-frequency wireless communication.

3. The intelligent scheduling method based on the artificial intelligence large model according to claim 1, wherein S2: Generate a transportation scheduling route strategy for the current transportation vehicle based on the current transportation vehicle sensing data, transportation space environment data, transportation scheduling route information, collaborative information of transportation vehicles in the same space, and an artificial intelligence large model, including: Determine the minimum scheduling boundary position information of the end freight hub group based on the end position information in the current transportation scheduling route information; Build an intelligent model for transportation scheduling route planning; Input the current transportation vehicle sensing data, transportation space environment data, and transportation scheduling route information into the intelligent model for transportation scheduling route planning to obtain the initial planned transportation scheduling route of the current transportation vehicle; Obtain the initial planned transportation scheduling routes of all transportation vehicles in the same space of the current transportation vehicle based on the collaborative information of transportation vehicles in the same space; Generate a transportation scheduling route strategy for the current transportation vehicle based on the initial planned transportation scheduling route of the current transportation vehicle and the initial planned transportation scheduling routes of all transportation vehicles in the same space of the current transportation vehicle.

4. The intelligent scheduling method based on the artificial intelligence large model according to claim 3, wherein, Generate a transportation scheduling route strategy for the current transportation vehicle based on the initial planned transportation scheduling route of the current transportation vehicle and the initial planned transportation scheduling routes of all transportation vehicles in the same space of the current transportation vehicle, including: Dynamically simulate the initial planned transportation scheduling route of the current transportation vehicle based on the current transportation vehicle sensing data, transportation space environment data, and transportation scheduling route information to obtain the initial planned dynamic transportation scheduling route of the current transportation vehicle; Dynamically simulate the initial planned transportation scheduling route of each co - space transportation vehicle of the current transportation vehicle based on the transportation vehicle sensing data, transportation space environment data, and transportation scheduling route information of each co - space transportation vehicle of the current transportation vehicle to obtain the initial planned dynamic transportation scheduling route of each co - space transportation vehicle of the current transportation vehicle; Determine whether there is an intersection between the initial planned dynamic transportation scheduling route of the current transportation vehicle and the initial planned dynamic transportation scheduling routes of all co - space transportation vehicles of the current transportation vehicle. If so, optimize the initial planned dynamic transportation scheduling route of the current transportation vehicle or the initial planned dynamic transportation scheduling routes of all co - space transportation vehicles of the current transportation vehicle to obtain the transportation scheduling route scheduling strategy of the current transportation vehicle. Otherwise, generate the transportation scheduling route scheduling strategy of the current transportation vehicle based on the initial planned dynamic transportation scheduling route of the current transportation vehicle.

5. The intelligent scheduling method based on the artificial intelligence large model according to claim 4, wherein, Optimize the initial planned dynamic transportation scheduling route of the current transportation vehicle or the initial planned dynamic transportation scheduling routes of all co - space transportation vehicles of the current transportation vehicle to obtain the transportation scheduling route scheduling strategy of the current transportation vehicle, including: Regard all intersection positions in the initial planned dynamic transportation scheduling route of the current transportation vehicle as all positions to be optimized, and regard the current transportation vehicle and all co - space transportation vehicles whose corresponding initial planned dynamic transportation routes cross at each position to be optimized as all alternative optimized transportation vehicles for transportation scheduling routes at each position to be optimized; Based on the transportation vehicle sensing data, transportation space environment data, and transportation scheduling route information of all alternative optimized transportation vehicles for transportation scheduling routes at each position to be optimized, calculate the optimizability of the transportation scheduling routes of all alternative optimized transportation vehicles for transportation scheduling routes at each corresponding position to be optimized; Regard all alternative optimized transportation vehicles for transportation scheduling routes at each position to be optimized except the alternative optimized transportation vehicle for the transportation scheduling route with the minimum optimizability as the target optimized transportation vehicle for the transportation scheduling route at each position to be optimized; Perform transportation scheduling route avoidance optimization on the initial planned dynamic transportation scheduling routes of the target optimized transportation vehicles for transportation scheduling routes corresponding to all positions to be optimized to obtain the final planned dynamic transportation scheduling route of the current transportation vehicle as the transportation scheduling route scheduling strategy of the current transportation vehicle.

6. The intelligent scheduling method based on the artificial intelligence large model according to claim 5, wherein Based on the transportation vehicle sensing data, transportation space environment data, and transportation scheduling route information of all alternative optimized transportation vehicles for transportation scheduling routes at each position to be optimized, calculate the optimizability of the transportation scheduling routes of all alternative optimized transportation vehicles for transportation scheduling routes at each corresponding position to be optimized, including: Based on the transportation vehicle sensing data, transportation space environment data, and transportation scheduling route information of all alternative optimized transportation vehicles for each position to be optimized, calculate the first degree of optimizability of the transportation scheduling route of each alternative optimized transportation vehicle for each position to be optimized at the corresponding position to be optimized; Based on the driving directions and driving speeds of all alternative optimized transportation vehicles for each position to be optimized at the corresponding position to be optimized, calculate the second degree of optimizability of the transportation scheduling route of each alternative optimized transportation vehicle for each position to be optimized at the corresponding position to be optimized; Based on the first degree of optimizability and the second degree of optimizability of the transportation scheduling route of each alternative optimized transportation vehicle for each position to be optimized at the corresponding position to be optimized, calculate the degree of optimizability of the transportation scheduling route of all alternative optimized transportation vehicles for each position to be optimized at the corresponding position to be optimized.

7. The intelligent scheduling method based on the large artificial intelligence model according to claim 6, wherein Based on the driving directions and driving speeds of all alternative optimized transportation vehicles for each position to be optimized at the corresponding position to be optimized, calculate the second degree of optimizability of the transportation scheduling route of each alternative optimized transportation vehicle for each position to be optimized at the corresponding position to be optimized, including: Where OD R2 is the optimizability of the second transportation scheduling route of the currently calculated alternative optimized transportation vehicle for the currently calculated position to be optimized at the corresponding position to be optimized, v max is the maximum driving speed that the currently calculated alternative optimized transportation vehicle of the transportation scheduling route can reach, v h is the driving speed of the currently calculated alternative optimized transportation vehicle of the transportation scheduling route at the currently calculated position to be optimized, C up is the acceleration cost of the currently calculated alternative optimized transportation vehicle of the transportation scheduling route, v min is the minimum driving speed that the currently calculated alternative optimized transportation vehicle of the transportation scheduling route can reach, C down is the deceleration cost of the currently calculated alternative optimized transportation vehicle of the transportation scheduling route, α1 is the driving speed optimization weight, a h1 is the driving direction of the first alternative optimized transportation vehicle of the transportation scheduling route if there are only 2 alternative optimized transportation vehicles for the transportation scheduling route at the currently calculated position to be optimized, a h2 is the driving direction of the second alternative optimized transportation vehicle of the transportation scheduling route if there are only 2 alternative optimized transportation vehicles for the transportation scheduling route at the currently calculated position to be optimized, I(a h1 , a h2 ) is the included angle between the driving directions of the two corresponding alternative optimized transportation vehicles of the transportation scheduling route if there are only 2 alternative optimized transportation vehicles for the transportation scheduling route at the currently calculated position to be optimized, α2 is the driving direction optimization weight, n is the total number of alternative optimized transportation vehicles of the transportation scheduling route at the currently calculated position to be optimized, a h0 is the driving direction of the currently calculated alternative optimized transportation vehicle of the transportation scheduling route, a hi is the driving direction of the i-th alternative optimized transportation vehicle of the transportation scheduling route among all alternative optimized transportation vehicles of the transportation scheduling route at the currently calculated position to be optimized except the currently calculated alternative optimized transportation vehicle, and i = 3, 4, 5…, n, max[I(a h0 , a hi )] is the maximum value among the included angles between the driving direction of the currently calculated alternative optimized transportation vehicle of the transportation scheduling route and the driving directions of all alternative optimized transportation vehicles of the transportation scheduling route at the currently calculated position to be optimized except the currently calculated alternative optimized transportation vehicle.

8. The intelligent scheduling method based on the artificial intelligence large model according to claim 1, wherein S3: Based on the current cargo information, freight hub information, co-space transportation vehicle collaboration information, and artificial intelligence large model, generate the terminal freight hub scheduling strategy for the current transportation vehicle, including: Build a loading and unloading requirement matching evaluation intelligent model; Input the cargo type and loading and unloading requirements in the current cargo information and the loading and unloading equipment status information of each terminal freight hub of the current transportation vehicle 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; Regard all terminal freight hubs with a current loading and unloading demand matching degree not less than the loading and unloading demand matching degree threshold among all terminal freight hubs of the current transportation vehicle as the current alternative freight hubs; Based on the current cargo information, the current freight hub information, co-space transportation vehicle collaboration information, transportation scheduling route scheduling strategy, and artificial intelligence large model, determine the predicted busyness of each current alternative freight hub; Regard the alternative freight hub with the minimum predicted busyness among all current alternative freight hubs as the target arrival freight hub; Generate the terminal freight hub scheduling strategy based on the target arrival freight hub.

9. The intelligent scheduling method based on the large artificial intelligence model according to claim 8, wherein Based on the current cargo information, the current freight hub information, co-space transportation vehicle collaboration information, transportation scheduling route scheduling strategy, and artificial intelligence large model, determine the predicted busyness of each current alternative freight hub, including: Build a freight hub busyness prediction intelligent model; Input the current cargo information, the current freight hub information, co-space transportation vehicle collaboration information, and transportation scheduling route scheduling strategy into the freight hub busyness prediction intelligent model to obtain the predicted busyness of each current alternative freight hub.

10. An intelligent scheduling system based on an artificial intelligence large model, characterized in that, For implementing the intelligent scheduling method based on the artificial intelligence large model described in any one of claims 1 to 9, including: An information collection module, which is used to collect current transportation vehicle sensing data, transportation space environment data, transportation scheduling route information, cargo information, freight hub information, and transportation vehicle collaboration information in the same space; A transportation scheduling route scheduling module, which is used to generate a transportation scheduling route scheduling strategy for the current transportation vehicle based on the current transportation vehicle sensing data, transportation space environment data, transportation scheduling route information, cargo information, and transportation vehicle collaboration information in the same space, as well as an artificial intelligence large model; A freight hub scheduling module, which is used to generate an end freight hub scheduling strategy for the current transportation vehicle based on the current cargo information, freight hub information, transportation vehicle collaboration information in the same space, and an artificial intelligence large model; A comprehensive scheduling module, which is used to merge the transportation scheduling route scheduling strategy and the end freight hub scheduling strategy of the current transportation vehicle to obtain the transportation scheduling strategy of the current transportation vehicle.

Images