Electric road bulk logistics transportation AI intelligent scheduling management and control method and system

Abstract

The invention relates to the technical field of road comprehensive management and control, and particularly discloses an electrified road bulk logistics transportation AI intelligent scheduling management and control method and system, and the method comprises the steps: receiving order information, and matching a target vehicle according to the order information; determining a preset number of vehicle paths according to a starting point and an ending point in the order information, marking an abnormal section in each vehicle path based on weather service, and updating the vehicle path according to a marking result; all vehicle paths are evaluated, and a final path is determined; vehicle parameters of the target vehicle are obtained in real time based on pre-obtained permissions, and a scheduling instruction pointing to the energy nodes is generated according to the vehicle parameters and sent to the target vehicle. The invention provides a comprehensive dispatching system oriented to multiple parties, after order information is received, target vehicles are matched, transportation tasks are generated, in the transportation process, vehicle information is obtained in real time, the vehicle transportation process is controlled, and coordination is extremely high.

Description

Technical Field

[0001] The present invention relates to the technical field of integrated highway management and control, and specifically to an AI intelligent dispatching and control method and system for bulk logistics transportation on electrified highways. Background Art

[0002] Electrified highways require the integration of multi-dimensional dynamic data such as grid load, vehicle battery status, road conditions, and cargo information. However, current platforms often rely on isolated subsystems, such as independent energy management systems and logistics scheduling systems, resulting in significant data interaction delays. Logistics companies, charging operators, and road management parties use heterogeneous data protocols, which requires the dispatch center to invest a lot of resources in cleaning and converting data, affecting decision-making timeliness. Therefore, how to provide a unified multi-party data management platform to improve the coordination of the electrified transportation process is the technical problem that the technical solution of the present invention aims to solve. Summary of the Invention

[0003] The purpose of the present invention is to provide an AI intelligent scheduling and control method and system for electrified highway bulk logistics transportation to solve the problems raised in the above background technology.

[0004] To achieve the above object, the present invention provides the following technical solutions:

[0005] An AI-powered intelligent dispatching and control method for bulk logistics transportation on electrified highways, the method comprising:

[0006] Receive order information, match target vehicles according to the order information, and simultaneously determine the weather requirements of the order information;

[0007] Determine a preset number of vehicle routes based on the start and end points in the order information, mark abnormal sections in each vehicle route based on weather services and weather requirements, and update the vehicle routes based on the marking results;

[0008] Based on the pre-acquired permissions, the energy node distribution information of each vehicle path is obtained, and the energy node distribution information is used as one of the indicators to evaluate all vehicle paths and determine the final path;

[0009] Based on the pre-acquired permissions, the vehicle parameters of the target vehicle are obtained in real time, and a scheduling instruction pointing to the energy node is generated according to the vehicle parameters and sent to the target vehicle.

[0010] As a further solution of the present invention, the steps of receiving order information, matching target vehicles according to the order information, and simultaneously determining the weather requirements of the order information include:

[0011] Receive order information and obtain cargo information in the order information; the cargo information includes: cargo type, weight, volume, place of shipment, destination, and time requirement;

[0012] Matching spare vehicles based on the shipping place and destination; the spare vehicles are determined by the vehicle location. When a vehicle's activity range includes the shipping place and destination and the distance between its current location and the shipping place is less than a preset distance threshold, it is marked as a spare vehicle;

[0013] Match the target vehicle among the available vehicles based on the type, weight and volume of the cargo;

[0014] Query weather requirements in the preset demand database based on the type of goods.

[0015] As a further solution of the present invention, the steps of determining a preset number of vehicle routes based on the starting point and the ending point in the order information, marking abnormal segments in each vehicle route based on weather services and weather requirements, and updating the vehicle routes based on the marking results include:

[0016] Read the place of shipment in the order information as the starting point, and read the destination in the order information as the end point;

[0017] Obtaining a vehicle path from a starting point to a destination based on a navigation service, executing the path in a loop and retaining non-duplicate vehicle paths, and outputting the vehicle path when the number of retained vehicle paths reaches a preset number; the vehicle path is a set of locations including predicted arrival times;

[0018] For any location along the vehicle’s route, query the weather service for the predicted arrival time at that location and compare it with the weather requirements;

[0019] When the weather information does not meet the weather requirements, the corresponding location is marked as an abnormal location;

[0020] The abnormal positions marked by the statistics are regarded as abnormal segments, and the abnormal segments are regarded as obstacle areas to update the vehicle path.

[0021] As a further solution of the present invention, the steps of obtaining energy node distribution information of each vehicle path based on the pre-acquired authority, evaluating all vehicle paths using the energy node distribution information as one of the indicators, and determining the final path include:

[0022] Obtain energy node distribution information based on pre-acquired permissions;

[0023] Querying the energy nodes that each vehicle path passes through to obtain energy node distribution information for each vehicle path; wherein, when the distance between the energy node and the vehicle path is less than a preset distance threshold, it is determined that the vehicle path passes through the energy node;

[0024] Accumulate the distance between each energy node on the vehicle path and the path itself, determine the weight based on the distance, obtain the average occupancy rate of each energy node, and accumulate the average occupancy rate based on the weight to obtain the comprehensive occupancy rate of the vehicle path;

[0025] Obtain the path length and path duration of the vehicle path, and determine the evaluation score of the vehicle path based on the path length, path duration, and comprehensive occupancy rate; wherein the path length, path duration, and comprehensive occupancy rate are all reverse indicators;

[0026] The vehicle path with the largest evaluation score is selected as the final path.

[0027] As a further solution of the present invention, the steps of obtaining vehicle parameters of the target vehicle in real time based on the pre-acquired authority, generating a dispatch instruction directed to the energy node according to the vehicle parameters, and sending the dispatch instruction to the target vehicle include:

[0028] Obtain vehicle parameters of the target vehicle in real time based on pre-acquired permissions;

[0029] Querying the remaining power and vehicle speed in the vehicle parameters, and determining a prediction range based on the remaining power and vehicle speed;

[0030] Query energy nodes within the forecast range and send a reservation request to the nearest energy node;

[0031] After receiving the feedback information from the energy node, the energy node is used as a waypoint and sent to the target vehicle;

[0032] The point where charging is completed is used as the new starting point to redefine the final route.

[0033] As a further embodiment of the present invention, the method further comprises:

[0034] Read the vehicle model, vehicle position and vehicle speed in the vehicle parameters of each vehicle;

[0035] determining a vehicle model according to the vehicle model;

[0036] inserting the vehicle model into a pre-established road model according to the vehicle position;

[0037] Insert vehicle speed as a label into the vehicle model.

[0038] The technical solution of the present invention also provides an AI intelligent dispatching and control system for electrified highway bulk logistics transportation, the system comprising:

[0039] The vehicle matching module is used to receive order information, match target vehicles according to the order information, and simultaneously determine the weather requirements of the order information;

[0040] A route updating module is used to determine a preset number of vehicle routes based on the start and end points in the order information, mark abnormal sections in each vehicle route based on weather services and weather requirements, and update the vehicle routes based on the marking results;

[0041] A final path determination module is used to obtain the energy node distribution information of each vehicle path based on the pre-acquired permissions, and use the energy node distribution information as one of the indicators to evaluate all vehicle paths and determine the final path;

[0042] The scheduling instruction generation module is used to obtain the vehicle parameters of the target vehicle in real time based on the pre-acquired permissions, generate a scheduling instruction pointing to the energy node according to the vehicle parameters, and send it to the target vehicle.

[0043] As a further solution of the present invention: the vehicle matching module includes:

[0044] A cargo information acquisition unit, configured to receive order information and acquire cargo information from the order information; the cargo information includes: cargo type, weight, volume, place of shipment, destination, and time requirement;

[0045] A spare vehicle marking unit is used to match spare vehicles according to the shipping place and the destination; the spare vehicles are determined by the vehicle position, and when the activity range of a certain vehicle includes the shipping place and the destination and the distance between the current position and the shipping place is less than a preset distance threshold, it is marked as a spare vehicle;

[0046] a target vehicle acquisition unit, configured to match a target vehicle among the backup vehicles according to the type, weight and volume of the cargo;

[0047] The weather demand query unit is used to query weather demand in a preset demand library according to the type of goods.

[0048] As a further solution of the present invention: the path updating module includes:

[0049] The point reading unit is used to read the place of shipment in the order information as the starting point and the destination in the order information as the end point;

[0050] a path output unit, configured to obtain a vehicle path from a start point to a destination based on a navigation service, execute the path cyclically and retain non-duplicate vehicle paths, and output the vehicle path when the number of retained vehicle paths reaches a preset number; the vehicle path is a collection of locations with predicted arrival times;

[0051] An information comparison unit is used to query the weather information of the predicted arrival time at any location in the vehicle path based on the weather service and compare it with the weather requirements;

[0052] A location marking unit is used to mark the corresponding location as an abnormal location when the weather information does not meet the weather requirements;

[0053] The position statistics unit is used to count the abnormal positions marked as abnormal segments, and use the abnormal segments as obstacle areas to update the vehicle path.

[0054] As a further solution of the present invention: the final path determination module includes:

[0055] A distribution information acquisition unit, configured to acquire energy node distribution information based on pre-acquired permissions;

[0056] A point classification unit is used to query the energy nodes passed by each vehicle path and obtain the energy node distribution information of each vehicle path; when the distance between the energy node and the vehicle path is less than a preset distance threshold, it is determined that the vehicle path passes through the energy node;

[0057] an occupancy analysis unit, configured to accumulate the distance between each energy node on the vehicle path and the path itself, determine a weight based on the distance, obtain an average occupancy of each energy node, and accumulate the average occupancy based on the weight to obtain a comprehensive occupancy of the vehicle path;

[0058] An evaluation score calculation unit is used to obtain the path length and path duration of the vehicle path, and determine the evaluation score of the vehicle path based on the path length, path duration, and comprehensive occupancy rate; wherein the path length, path duration, and comprehensive occupancy rate are all reverse indicators;

[0059] The evaluation score application unit is used to select the vehicle path with the largest evaluation score as the final path.

[0060] Compared with the existing technology, the beneficial effects of the present invention are: the present invention provides a comprehensive scheduling system for multiple parties. After receiving the order information, it matches the target vehicle and generates the transportation task. During the transportation process, it obtains vehicle information in real time and controls the vehicle transportation process with strong coordination. BRIEF DESCRIPTION OF THE DRAWINGS

[0061] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are only some embodiments of the present invention.

[0062] Figure 1 This is a flowchart of the AI ​​intelligent scheduling and control method for bulk logistics transportation on electrified roads.

[0063] Figure 2 This is the first sub-process flowchart of the AI ​​intelligent scheduling and control method for bulk logistics transportation on electrified roads.

[0064] Figure 3 This is the second sub-process flowchart of the AI ​​intelligent scheduling and control method for bulk logistics transportation on electrified roads.

[0065] Figure 4 This is the third sub-process flowchart of the AI ​​intelligent scheduling and control method for bulk logistics transportation on electrified roads.

[0066] Figure 5 This is the fourth sub-process flowchart of the AI ​​intelligent scheduling and control method for bulk logistics transportation on electrified roads.

[0067] Figure 6 This is a structural block diagram of the AI ​​intelligent dispatching and control system for bulk logistics transportation on electrified roads. DETAILED DESCRIPTION

[0068] In order to make the technical problems, technical solutions and beneficial effects to be solved by the present invention more clearly understood, the present invention is further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not intended to limit the present invention.

[0069] Figure 1 This is a flowchart of an AI-powered intelligent dispatching and control method for bulk logistics transportation on electrified highways. In an embodiment of the present invention, an AI-powered intelligent dispatching and control method for bulk logistics transportation on electrified highways includes:

[0070] Step S100: receiving order information, matching target vehicles according to the order information, and simultaneously determining the weather requirements of the order information;

[0071] Receive order information, which is generally uploaded by the shipper, and match a vehicle based on the order information. The vehicle that completes the order is called the target vehicle. The order information also includes weather requirements, for example, some goods cannot pass through rainy areas.

[0072] Step S200: determining a preset number of vehicle routes based on the starting point and the end point in the order information, marking abnormal sections in each vehicle route based on weather services and weather requirements, and updating the vehicle route based on the marking results;

[0073] The starting point and end point in the order information are read, and the vehicle path from the starting point to the end point is determined with the help of a map service. Under the existing road network architecture, there are many types of vehicle paths. Enumeration is one solution, but the number is too large. The present invention limits the number of paths, that is, there is a preset number; then, based on the weather service, the weather conditions of each location on the vehicle path are queried to determine whether the weather requirements are met. If not, the corresponding location is marked as an abnormal location, thereby obtaining an abnormal segment. The abnormal segment is regarded as an area not passed through, and the vehicle path can be updated.

[0074] Step S300: obtaining energy node distribution information of each vehicle path based on the pre-acquired authority, using the energy node distribution information as one of the indicators to evaluate all vehicle paths and determine the final path;

[0075] After each vehicle path is updated, the energy node distribution information of each vehicle path is obtained based on the pre-acquired permissions. That is, which energy nodes the vehicle path passes through? The energy node distribution information is used as one of the indicators to evaluate all vehicle paths and determine the final path. In fact, in addition to the energy node distribution information indicator, there are also path length indicators and path duration indicators.

[0076] Step S400: obtaining vehicle parameters of the target vehicle in real time based on the pre-acquired authority, generating a dispatch instruction directed to the energy node according to the vehicle parameters, and sending the instruction to the target vehicle;

[0077] The vehicle parameters of the target vehicle are obtained in real time based on the pre-acquired permissions. The vehicle parameters are information about the vehicle itself and can only be obtained with explicit authorization. A dispatch instruction pointing to the energy node is generated based on the acquired vehicle parameters and sent to the target vehicle, so that the target vehicle can replenish electricity. In actual applications, the target vehicle is generally a new energy electric vehicle, and in the future it may even be an unmanned new energy electric vehicle. This self-replenishing power control system can make its distribution process extremely coordinated.

[0078] Figure 2 This is a flowchart of the first sub-process of the AI ​​intelligent dispatching and control method for electrified highway bulk logistics transportation. The steps of receiving order information, matching target vehicles according to the order information, and simultaneously determining the weather requirements of the order information include:

[0079] Step S101: Receive order information and obtain cargo information in the order information; the cargo information includes: cargo type, weight, volume, shipping place, destination, and time requirement;

[0080] Step S102: Matching a spare vehicle based on the shipping place and the destination; the spare vehicle is determined by the vehicle location. When a vehicle's activity range includes the shipping place and the destination and the distance between its current location and the shipping place is less than a preset distance threshold, it is marked as a spare vehicle;

[0081] Step S103: Matching a target vehicle among the spare vehicles according to the type, weight and volume of the cargo;

[0082] Step S104: querying weather requirements in a preset demand database according to the type of goods.

[0083] In one example of the technical solution of the present invention, order information is received and cargo information in the order information is obtained; the cargo information includes: the type, weight, volume, place of shipment, destination and time requirement of the cargo; for vehicles that can be put into use, their activity range is obtained (some vehicles cannot leave the area); when the activity range of a certain vehicle includes the place of shipment and destination and the distance between the current position and the place of shipment is less than a preset distance threshold, it is marked as a spare vehicle, and then, according to the type, weight and volume of the cargo, a vehicle that can meet the demand is matched among the spare vehicles, which is called a target vehicle; finally, according to the type of cargo, weather requirements are queried in a preset demand library.

[0084] It should be noted that the time requirement is generally used in the vehicle route selection process to eliminate some vehicle routes that exceed the time requirement.

[0085] Figure 3 This is a flowchart of the second sub-process of the AI ​​intelligent scheduling and control method for electrified highway bulk logistics transportation. The steps of determining a preset number of vehicle routes based on the starting and ending points in the order information, marking abnormal sections in each vehicle route based on weather services and weather requirements, and updating the vehicle routes based on the marking results include:

[0086] Step S201: Read the place of shipment in the order information as the starting point, and read the destination in the order information as the end point;

[0087] Step S202: Obtaining a vehicle path from a starting point to a destination based on a navigation service, executing the process in a loop and retaining non-duplicate vehicle paths, and outputting the vehicle paths when the number of retained vehicle paths reaches a preset number; the vehicle paths are a collection of locations with predicted arrival times;

[0088] Step S203: For any location in the vehicle route, query the weather information of the predicted arrival time at the location based on the weather service, and compare it with the weather requirements;

[0089] Step S204: When the weather information does not meet the weather requirements, the corresponding location is marked as an abnormal location;

[0090] Step S205: Count the abnormal positions marked as abnormal segments, treat the abnormal segments as obstacle areas, and update the vehicle path.

[0091] In an example of the technical solution of the present invention, the vehicle path update process is described. The shipping place in the order information is read as the starting point, and the destination in the order information is read as the end point. The vehicle path from the starting point to the end point is obtained based on the navigation service. The loop is executed and non-repeated vehicle paths are retained. When the number of retained vehicle paths reaches a preset number, the vehicle path is output. The vehicle path is a collection of locations with predicted arrival times. In the process of retaining non-repeated vehicle paths, time conditions can also be introduced to retain vehicle paths that meet time requirements.

[0092] For any location in the vehicle path, the weather information of the predicted arrival time of the location is queried based on the weather service and compared with the weather requirements. When the weather information does not meet the weather requirements, the corresponding location is marked as an abnormal location, and the marked abnormal locations are counted as abnormal segments. The abnormal segments are regarded as obstacle areas and the vehicle path is updated.

[0093] Figure 4 This is a flowchart of the third sub-process of the AI ​​intelligent scheduling and control method for electrified highway bulk logistics transportation. The steps of obtaining energy node distribution information for each vehicle path based on pre-acquired permissions, using energy node distribution information as one of the indicators to evaluate all vehicle paths, and determining the final path include:

[0094] Step S301: Obtain energy node distribution information based on pre-acquired authority;

[0095] Step S302: querying the energy nodes that each vehicle path passes through to obtain energy node distribution information for each vehicle path; wherein, when the distance between the energy node and the vehicle path is less than a preset distance threshold, it is determined that the vehicle path passes through the energy node;

[0096] Step S303: Accumulating the distance between each energy node on the vehicle path and the path itself, determining a weight based on the distance, obtaining the average occupancy rate of each energy node, and accumulating the average occupancy rate based on the weight to obtain the comprehensive occupancy rate of the vehicle path;

[0097] Step S304: Obtain the path length and path duration of the vehicle path, and determine the evaluation score of the vehicle path based on the path length, path duration, and comprehensive occupancy rate; wherein the path length, path duration, and comprehensive occupancy rate are all inverse indicators;

[0098] Step S305: Select the vehicle path with the largest evaluation score as the final path.

[0099] In an example of the technical solution of the present invention, the vehicle path selection process is explained. The energy node distribution information is obtained based on the pre-acquired authority. The energy node is the location where charging can be performed. The energy nodes passed by each vehicle path are queried to obtain the energy node distribution information of each vehicle path. The judgment standard for passing is: when the distance between the energy node and the vehicle path is less than the preset distance threshold, it is determined that the vehicle path passes through the energy node.

[0100] Accumulate the distance between each energy node on the vehicle path and the path itself, determine the weight based on the distance, obtain the average occupancy rate of each energy node, and accumulate the average occupancy rate according to the weight to obtain the comprehensive occupancy rate of the vehicle path. The weight is proportional to the distance, so that the "occupancy rate" of the energy node with a longer distance is higher. Obtain the path length and path duration of the vehicle path, and determine the evaluation score of the vehicle path based on the path length, path duration and comprehensive occupancy rate. The path length, path duration and comprehensive occupancy rate are all inverse indicators, that is, the evaluation score is inversely proportional to these parameters. Select the vehicle path with the largest evaluation score as the final path.

[0101] Figure 5 This is a flowchart of the fourth sub-process of the AI ​​intelligent dispatching and control method for electrified highway bulk logistics transportation. The steps of obtaining the vehicle parameters of the target vehicle in real time based on the pre-acquired permissions, generating a dispatch instruction directed to the energy node based on the vehicle parameters, and sending it to the target vehicle include:

[0102] Step S401: obtaining vehicle parameters of the target vehicle in real time based on the pre-acquired authority;

[0103] Step S402: querying the remaining power and vehicle speed in the vehicle parameters, and determining a prediction range based on the remaining power and vehicle speed;

[0104] Step S403: querying energy nodes within the prediction range, and sending a reservation request to the nearest energy node found;

[0105] Step S404: After receiving the feedback information from the energy node, the energy node is used as a waypoint and sent to the target vehicle;

[0106] Step S405: The waypoint at the time of charging completion is used as a new starting point to redetermine the final path.

[0107] In an example of the technical solution of the present invention, the analysis process of the vehicle parameters is explained. The vehicle parameters of the target vehicle are obtained in real time based on the pre-acquired permissions, the remaining power and vehicle speed in the vehicle parameters are queried, and the prediction range is determined based on the remaining power and vehicle speed. One way to determine the prediction range is: a circular range with the vehicle position as the center and the cruising range (determined by the remaining power) as the radius, and then a semicircle is intercepted according to the direction of the vehicle speed to obtain the final prediction range.

[0108] The system queries energy nodes within the predicted range and sends a reservation request to the nearest energy node. After receiving feedback from the energy node, it sends the energy node as a waypoint to the target vehicle. The feedback information indicates whether charging is possible. If not, the energy node is deleted within the predicted range, and then the nearest energy node is determined. The operation is repeated until charging is possible.

[0109] As a preferred embodiment of the technical solution of the present invention, the method further includes:

[0110] Read the vehicle model, vehicle position and vehicle speed in the vehicle parameters of each vehicle;

[0111] determining a vehicle model according to the vehicle model;

[0112] inserting the vehicle model into a pre-established road model according to the vehicle position;

[0113] Insert vehicle speed as a label into the vehicle model.

[0114] In one example of the technical solution of the present invention, a modeling and display solution is also provided, which reads the vehicle model and vehicle position in the vehicle parameters of each vehicle, determines the vehicle model based on the vehicle model, and inserts the vehicle model into a pre-established highway model based on the vehicle position; further, obtains the vehicle speed of the vehicle, uses the vehicle speed as a label, and inserts it into the vehicle model.

[0115] As a preferred embodiment of the technical solution of the present invention, a feasible implementation architecture is also provided as follows:

[0116] 1. System architecture construction:

[0117] (1) Construction of the perception layer: Various sensors are widely deployed along electrified highways, such as roadside radars for accurate monitoring of vehicle speed, distance, and number; video sensors for real-time road image capture, identification of vehicle type, driving status, and traffic events; and power sensors for obtaining battery status of electric transport vehicles. At the same time, each vehicle involved in bulk logistics transportation is equipped with an onboard terminal that integrates a GPS positioning module for real-time tracking of the vehicle's location, as well as a communication module to ensure stable data transmission between the vehicle and the platform. For example, on key electrified sections such as the Lianhuo Expressway, the dense deployment of these sensing devices enables comprehensive and timely collection of vehicle-road-electricity and other data.

[0118] (2) Network layer construction: 5G communication technology is used as the backbone network, and its high speed and low latency characteristics are utilized to ensure that the massive data collected by the perception layer can be transmitted to the platform quickly and stably. At the same time, it is supplemented by the fiber optic network. In some areas with weak signals or extremely high requirements for data transmission stability, reliable data return can be achieved through optical fiber. For some remote areas or sections of road with difficult signal coverage, satellite communication is introduced as a backup communication method to ensure uninterrupted data communication during the entire transportation process, providing a solid network foundation for the platform's real-time monitoring and intelligent scheduling.

[0119] (3) Platform layer architecture: The platform infrastructure is built based on cloud computing technology, which has powerful computing and storage capabilities and can efficiently process and store massive amounts of transportation data. The platform layer mainly includes a data processing center, an AI intelligent dispatching center, and a monitoring and management center. The data processing center is responsible for cleaning, integrating, and pre-processing the raw data transmitted from the perception layer, converting it into effective data for analysis and decision-making; the AI ​​intelligent dispatching center uses various intelligent algorithms, such as machine learning algorithms, to conduct in-depth mining of historical transportation data, and generates the optimal dispatching plan based on factors such as real-time road conditions, vehicle status, and transportation demand; the monitoring and management center uses a visual interface to monitor the entire electrified highway transportation network in real time, including vehicle location, driving status, power status, and road facility status, so that managers can grasp transportation dynamics in a timely manner and make decisions.

[0120] (4) Application layer function development: Develop targeted application functions for different user roles. For transportation companies, provide vehicle scheduling management functions, so that they can flexibly arrange vehicle transportation tasks according to the scheduling plan generated by the platform; transportation plan formulation functions, which can combine market demand and enterprise resources to formulate long-term or short-term transportation plans; and vehicle status monitoring functions, which can provide real-time information on the operation status of the company's vehicles. For drivers, it is equipped with navigation and path planning applications, which plan the optimal driving route for drivers based on the platform's scheduling instructions and real-time road conditions, and update route information in real time during driving; power management and charging reminder functions, which help drivers reasonably arrange power usage and promptly remind drivers to go to appropriate charging stations for charging. For managers, set up a transportation monitoring and decision support system, through a large visual screen, to fully grasp the overall operation status of the transportation network, and use the data analysis and prediction functions provided by the platform to provide a scientific basis for management decisions.

[0121] 2. Data collection and processing:

[0122] (1) Multi-source data collection: In addition to the vehicle-road related data collected by the perception layer equipment, other transportation-related data are also widely collected. For example, real-time meteorological information, including weather conditions, wind speed, precipitation, etc., is obtained from the meteorological department, because bad weather may have a significant impact on transportation safety and efficiency. Traffic rules and restrictions are obtained from the traffic management department to ensure that the operation of transport vehicles complies with legal requirements. Cargo information, such as cargo type, weight, volume, place of shipment, destination, and transportation time requirements, is obtained from the logistics order system, so that reasonable vehicle allocation and route planning can be carried out according to the characteristics of the cargo. By connecting with the energy supply department for data, information such as the location, quantity, usage status, and electricity price of charging piles is obtained to provide support for the energy supply of electric vehicles.

[0123] (2) Data cleaning and preprocessing: Since the collected data comes from a wide range of sources and in various formats, and may contain noise and erroneous data, data cleaning and preprocessing are required. Use data cleaning algorithms to identify and remove duplicate data, erroneous data, and outliers. For example, verify and correct vehicle speed data or power data collected by sensors that clearly deviate from the normal range. Standardize data in different formats and convert them into a format that the platform can recognize and process. At the same time, fill in missing data using methods such as mean filling, interpolation, or predictive filling based on machine learning models to ensure data integrity and provide a high-quality data foundation for subsequent data analysis and intelligent scheduling.

[0124] (3) Data analysis and mining: Use big data analysis technology to conduct in-depth analysis of the processed data. By mining historical transportation data, the seasonal and regional characteristics of freight demand and industry development trends can be identified. For example, the analysis of the changing patterns of transportation demand for various types of bulk goods in different regions in different seasons can provide a reference for transportation companies to make resource allocation and transportation plans in advance. Use association analysis algorithms to find the correlation between cargo type, transportation route, transportation time and transportation cost, so as to optimize transportation plans and reduce costs. Through cluster analysis, the driving behavior and energy consumption of vehicles are classified to provide guidance for vehicle maintenance and energy-saving driving. In addition, machine learning algorithms can be used to establish prediction models. For example, based on real-time road conditions, weather conditions and historical data, traffic flow and transportation time in the future can be predicted to provide more accurate decision-making basis for intelligent scheduling.

[0125] 3. Application of AI intelligent scheduling algorithm:

[0126] (1) Intelligent matching of orders and vehicles: The AI ​​intelligent dispatching system realizes intelligent matching of orders and vehicles through comprehensive analysis of logistics order information and vehicle information. First, the type, load capacity, range and other factors of the vehicle are considered to screen out vehicles that meet the requirements of cargo transportation. Then, the optimization algorithm is used to calculate the optimal matching solution based on the current location and driving status of the vehicle, as well as the urgency of the order, the place of shipment and the destination. For example, for a batch of bulk cargo orders with heavy weight and long transportation distance, electric transport vehicles with long range, strong load capacity and current location close to the place of shipment are given priority. Through this intelligent matching method, the order completion rate is improved, the vehicle idle rate is reduced, and the transportation efficiency is improved.

[0127] (2) Dynamic route planning: Based on real-time road condition information, traffic control conditions, and the vehicle's driving status, the AI ​​algorithm dynamically plans the optimal driving route for the transport vehicle. When planning the route, multiple factors are taken into consideration, such as the route distance, expected driving time, road congestion level, road height and weight restrictions, and the distribution of charging facilities. Using real-time traffic data, the system can promptly detect congested sections of the road and automatically adjust the route to avoid congested areas and choose a faster alternative route. For example, when a traffic accident causes congestion on a major transport route, the system quickly replans a route for the vehicle that passes through surrounding roads to ensure that the goods can be delivered on time. At the same time, combined with the vehicle's power level, a route that includes the best charging station is planned to ensure that the vehicle will not be affected by insufficient power during transportation.

[0128] (3) Vehicle dispatch optimization: The AI ​​intelligent dispatch system comprehensively optimizes vehicle dispatch. In terms of vehicle allocation, vehicle resources are reasonably allocated based on the number of orders, cargo characteristics, transportation time requirements, and vehicle availability to ensure that each order can be transported by the most appropriate vehicle. In terms of vehicle dispatch order, a sorting algorithm is used to comprehensively consider factors such as the urgency of the order, the vehicle's driving distance, and the estimated arrival time to determine the optimal dispatch order to improve overall transportation efficiency. For vehicle return planning, the system analyzes the freight demand in the return direction and tries to arrange the vehicle to undertake other transportation tasks on the return trip, reducing empty mileage and improving vehicle utilization. Through these optimization measures, intelligent and efficient vehicle dispatch is achieved.

[0129] (4) Energy consumption management and optimization: For electric vehicles in electrified road transport, AI algorithms manage and optimize the energy consumption of vehicles. By analyzing the vehicle's driving data, battery performance data, and road condition information, a vehicle energy consumption model is established. Based on this model, the system can predict the vehicle's energy consumption under different driving conditions and provide the driver with energy-saving driving suggestions, such as reasonable speed control, avoiding sudden acceleration and braking, etc. During the vehicle dispatch process, the vehicle's energy consumption factors are taken into consideration, and vehicles with lower energy consumption are given priority to perform transportation tasks. At the same time, based on real-time road conditions and vehicle power, the vehicle's driving speed and power output are intelligently adjusted to minimize energy consumption. For example, when the vehicle's power is low and it is far away from the charging station, the system automatically reduces the vehicle's maximum speed limit and optimizes power distribution to ensure that the vehicle can reach the charging station smoothly while reducing energy consumption.

[0130] Figure 6 The following is a structural block diagram of an AI intelligent dispatching and control system for bulk logistics transportation on electrified highways. In an embodiment of the present invention, an AI intelligent dispatching and control system for bulk logistics transportation on electrified highways is provided. The system 10 includes:

[0131] The vehicle matching module 11 is used to receive order information, match target vehicles according to the order information, and simultaneously determine the weather requirements of the order information;

[0132] a route updating module 12 for determining a preset number of vehicle routes based on the start and end points in the order information, marking abnormal segments in each vehicle route based on weather services and weather requirements, and updating the vehicle routes based on the marking results;

[0133] The final path determination module 13 is configured to obtain energy node distribution information of each vehicle path based on pre-acquired permissions, evaluate all vehicle paths using the energy node distribution information as one of the indicators, and determine the final path;

[0134] The dispatch instruction generation module 14 is used to obtain the vehicle parameters of the target vehicle in real time based on the pre-acquired authority, generate a dispatch instruction directed to the energy node according to the vehicle parameters, and send it to the target vehicle.

[0135] Furthermore, the vehicle matching module 11 includes:

[0136] A cargo information acquisition unit, configured to receive order information and acquire cargo information from the order information; the cargo information includes: cargo type, weight, volume, place of shipment, destination, and time requirement;

[0137] A spare vehicle marking unit is used to match spare vehicles according to the shipping place and the destination; the spare vehicles are determined by the vehicle position, and when the activity range of a certain vehicle includes the shipping place and the destination and the distance between the current position and the shipping place is less than a preset distance threshold, it is marked as a spare vehicle;

[0138] a target vehicle acquisition unit, configured to match a target vehicle among the backup vehicles according to the type, weight and volume of the cargo;

[0139] The weather demand query unit is used to query weather demand in a preset demand library according to the type of goods.

[0140] Specifically, the path updating module 12 includes:

[0141] The point reading unit is used to read the place of shipment in the order information as the starting point and the destination in the order information as the end point;

[0142] a path output unit, configured to obtain a vehicle path from a start point to a destination based on a navigation service, execute the path cyclically and retain non-duplicate vehicle paths, and output the vehicle path when the number of retained vehicle paths reaches a preset number; the vehicle path is a collection of locations with predicted arrival times;

[0143] An information comparison unit is used to query the weather information of the predicted arrival time at any location in the vehicle path based on the weather service and compare it with the weather requirements;

[0144] A location marking unit is used to mark the corresponding location as an abnormal location when the weather information does not meet the weather requirements;

[0145] The position statistics unit is used to count the abnormal positions marked as abnormal segments, and use the abnormal segments as obstacle areas to update the vehicle path.

[0146] Furthermore, the final path determination module 13 includes:

[0147] A distribution information acquisition unit, configured to acquire energy node distribution information based on pre-acquired permissions;

[0148] A point classification unit is used to query the energy nodes passed by each vehicle path and obtain the energy node distribution information of each vehicle path; when the distance between the energy node and the vehicle path is less than a preset distance threshold, it is determined that the vehicle path passes through the energy node;

[0149] an occupancy analysis unit, configured to accumulate the distance between each energy node on the vehicle path and the path itself, determine a weight based on the distance, obtain an average occupancy of each energy node, and accumulate the average occupancy based on the weight to obtain a comprehensive occupancy of the vehicle path;

[0150] An evaluation score calculation unit is used to obtain the path length and path duration of the vehicle path, and determine the evaluation score of the vehicle path based on the path length, path duration, and comprehensive occupancy rate; wherein the path length, path duration, and comprehensive occupancy rate are all reverse indicators;

[0151] The evaluation score application unit is used to select the vehicle path with the largest evaluation score as the final path.

[0152] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions and improvements made within the spirit and principles of the present invention should be included in the scope of protection of the present invention.

Claims

1. An AI intelligent dispatching and control method for bulk logistics transportation on electrified highways, characterized by: The method comprises: Receive order information, match target vehicles according to the order information, and simultaneously determine the weather requirements of the order information; Determine a preset number of vehicle routes based on the start and end points in the order information, mark abnormal sections in each vehicle route based on weather services and weather requirements, and update the vehicle routes based on the marking results; Based on the pre-acquired permissions, the energy node distribution information of each vehicle path is obtained, and the energy node distribution information is used as one of the indicators to evaluate all vehicle paths and determine the final path; Based on the pre-acquired permissions, the vehicle parameters of the target vehicle are obtained in real time, and a scheduling instruction pointing to the energy node is generated according to the vehicle parameters and sent to the target vehicle.

2. The AI ​​intelligent dispatching and control method for bulk logistics transportation on electrified highways according to claim 1 is characterized in that: The steps of receiving order information, matching target vehicles according to the order information, and simultaneously determining the weather requirements of the order information include: Receive order information and obtain cargo information in the order information; the cargo information includes: cargo type, weight, volume, place of shipment, destination, and time requirement; Matching spare vehicles based on the shipping place and destination; the spare vehicles are determined by the vehicle location. When a vehicle's activity range includes the shipping place and destination and the distance between its current location and the shipping place is less than a preset distance threshold, it is marked as a spare vehicle; Match the target vehicle among the available vehicles based on the type, weight and volume of the cargo; Query weather requirements in the preset demand database based on the type of goods.

3. The AI ​​intelligent dispatching and control method for bulk logistics transportation on electrified highways according to claim 1 is characterized in that: The steps of determining a preset number of vehicle routes based on the starting point and the end point in the order information, marking abnormal sections in each vehicle route based on weather services and weather requirements, and updating the vehicle routes based on the marking results include: Read the place of shipment in the order information as the starting point, and read the destination in the order information as the end point; Obtaining a vehicle path from a start point to a destination based on a navigation service, executing the path in a loop and retaining non-duplicate vehicle paths, and outputting the vehicle path when the number of retained vehicle paths reaches a preset number; the vehicle path is a set of locations including predicted arrival times; For any location along the vehicle’s route, query the weather service for the predicted arrival time at that location and compare it with the weather requirements; When the weather information does not meet the weather requirements, the corresponding location is marked as an abnormal location; The abnormal positions marked by the statistics are regarded as abnormal segments, and the abnormal segments are regarded as obstacle areas to update the vehicle path.

4. The AI ​​intelligent dispatching and control method for bulk logistics transportation on electrified highways according to claim 1 is characterized in that: The steps of obtaining energy node distribution information of each vehicle path based on the pre-acquired authority, evaluating all vehicle paths using the energy node distribution information as one of the indicators, and determining the final path include: Obtain energy node distribution information based on pre-acquired permissions; Querying the energy nodes that each vehicle path passes through to obtain energy node distribution information for each vehicle path; wherein, when the distance between the energy node and the vehicle path is less than a preset distance threshold, it is determined that the vehicle path passes through the energy node; Accumulate the distance between each energy node on the vehicle path and the path itself, determine the weight based on the distance, obtain the average occupancy rate of each energy node, and accumulate the average occupancy rate based on the weight to obtain the comprehensive occupancy rate of the vehicle path; Obtain the path length and path duration of the vehicle path, and determine the evaluation score of the vehicle path based on the path length, path duration, and comprehensive occupancy rate; wherein the path length, path duration, and comprehensive occupancy rate are all reverse indicators; The vehicle path with the largest evaluation score is selected as the final path.

5. The AI ​​intelligent dispatching and control method for bulk logistics transportation on electrified highways according to claim 1 is characterized in that: The steps of acquiring vehicle parameters of the target vehicle in real time based on the pre-acquired authority, generating a dispatch instruction directed to the energy node according to the vehicle parameters, and sending the dispatch instruction to the target vehicle include: Obtain vehicle parameters of the target vehicle in real time based on pre-acquired permissions; Querying the remaining power and vehicle speed in the vehicle parameters, and determining a prediction range based on the remaining power and vehicle speed; Query energy nodes within the forecast range and send a reservation request to the nearest energy node; After receiving the feedback information from the energy node, the energy node is used as a waypoint and sent to the target vehicle; The point where charging is completed is used as the new starting point to redefine the final route.

6. The AI ​​intelligent dispatching and control method for bulk logistics transportation on electrified highways according to claim 1 is characterized in that: The method further comprises: Read the vehicle model, vehicle position and vehicle speed in the vehicle parameters of each vehicle; determining a vehicle model according to the vehicle model; inserting the vehicle model into a pre-established road model according to the vehicle position; Insert vehicle speed as a label into the vehicle model.

7. An AI intelligent dispatching and control system for bulk logistics transportation on electrified highways, characterized by: The system comprises: The vehicle matching module is used to receive order information, match target vehicles according to the order information, and simultaneously determine the weather requirements of the order information; A route updating module is used to determine a preset number of vehicle routes based on the start and end points in the order information, mark abnormal sections in each vehicle route based on weather services and weather requirements, and update the vehicle routes based on the marking results; A final path determination module is used to obtain the energy node distribution information of each vehicle path based on the pre-acquired permissions, and use the energy node distribution information as one of the indicators to evaluate all vehicle paths and determine the final path; The scheduling instruction generation module is used to obtain the vehicle parameters of the target vehicle in real time based on the pre-acquired permissions, generate a scheduling instruction pointing to the energy node according to the vehicle parameters, and send it to the target vehicle.

8. The AI ​​intelligent dispatching and control system for bulk logistics transportation on electrified highways according to claim 7 is characterized in that: The vehicle matching module includes: A cargo information acquisition unit, configured to receive order information and acquire cargo information from the order information; the cargo information includes: cargo type, weight, volume, place of shipment, destination, and time requirement; A spare vehicle marking unit is used to match spare vehicles according to the shipping place and the destination; the spare vehicles are determined by the vehicle position, and when the activity range of a certain vehicle includes the shipping place and the destination and the distance between the current position and the shipping place is less than a preset distance threshold, it is marked as a spare vehicle; a target vehicle acquisition unit, configured to match a target vehicle among the backup vehicles according to the type, weight and volume of the cargo; The weather demand query unit is used to query weather demand in a preset demand library according to the type of goods.

9. The AI ​​intelligent dispatching and control system for bulk logistics transportation on electrified highways according to claim 7 is characterized in that: The path updating module includes: The point reading unit is used to read the place of shipment in the order information as the starting point and the destination in the order information as the end point; a path output unit, configured to obtain a vehicle path from a start point to a destination based on a navigation service, execute the path cyclically and retain non-duplicate vehicle paths, and output the vehicle path when the number of retained vehicle paths reaches a preset number; the vehicle path is a collection of locations with predicted arrival times; An information comparison unit is used to query the weather information of the predicted arrival time at any location in the vehicle path based on the weather service and compare it with the weather requirements; A location marking unit is used to mark the corresponding location as an abnormal location when the weather information does not meet the weather requirements; The position statistics unit is used to count the abnormal positions marked as abnormal segments, and use the abnormal segments as obstacle areas to update the vehicle path.

10. The AI ​​intelligent dispatching and control system for bulk logistics transportation on electrified highways according to claim 7 is characterized in that: The final path determination module includes: A distribution information acquisition unit, configured to acquire energy node distribution information based on pre-acquired permissions; A point classification unit is used to query the energy nodes passed by each vehicle path and obtain the energy node distribution information of each vehicle path; when the distance between the energy node and the vehicle path is less than a preset distance threshold, it is determined that the vehicle path passes through the energy node; an occupancy analysis unit, configured to accumulate the distance between each energy node on the vehicle path and the path itself, determine a weight based on the distance, obtain an average occupancy of each energy node, and accumulate the average occupancy based on the weight to obtain a comprehensive occupancy of the vehicle path; An evaluation score calculation unit is used to obtain the path length and path duration of the vehicle path, and determine the evaluation score of the vehicle path based on the path length, path duration, and comprehensive occupancy rate; wherein the path length, path duration, and comprehensive occupancy rate are all reverse indicators; The evaluation score application unit is used to select the vehicle path with the largest evaluation score as the final path.

Images