Logistics transportation vehicle scheduling method and related device

Abstract

The invention discloses a logistics transportation vehicle scheduling method and a related device, and relates to the technical field of logistics transportation, and the method comprises the steps: analyzing the priority of each cargo order based on cargo order data; carrying out scheduling analysis and order distribution of the logistics transportation vehicles in combination with load analysis, and obtaining a target order distribution scheme of each target logistics transportation vehicle; based on the current weather information, combining with the weighted directed graph to carry out weather influence analysis on passage of each road; traffic flow prediction of each road is carried out based on the multi-modal traffic data; carrying out transportation route planning based on the traffic flow prediction data and the weather influence data in combination with the priority of each cargo order and a target order allocation scheme; and analyzing the vehicle driving energy consumption and the vehicle loss cost of each initial transportation route to determine a target transportation route, and transmitting the target transportation route to the vehicle terminal. According to the invention, the planned target transportation route is more accurate, so that the target logistics transportation vehicle can be ensured to deliver goods in time.

Description

Technical Field

[0001] The present invention relates to the field of logistics and transportation technology, and in particular to a scheduling method and related devices for logistics and transportation vehicles. Background Art

[0002] With the development of the market economy, the scale of the logistics industry continues to grow, and the field of intelligent logistics has attracted more and more attention and research. One of the core issues is how to efficiently dispatch logistics vehicles to improve transportation efficiency and reduce costs. Order allocation is a key step in logistics vehicle scheduling. Current order allocation rarely takes into account the cargo load of the vehicle, resulting in some vehicles being overloaded. This problem affects the stability and safety of logistics vehicles and poses a significant risk to the logistics transportation process. At the same time, transportation route planning is also a key step in logistics vehicle scheduling. Currently, most methods directly use heuristic algorithms to plan transportation routes. However, this approach considers few constraints and fails to account for the impact of factors such as weather conditions, traffic flow, vehicle energy consumption, and loss costs on vehicle operation. The planned transportation routes may deviate significantly from the actual drivable routes, resulting in significant constraints on the actual operation of logistics vehicles, which in turn affects the driving speed of logistics vehicles and delays the arrival time of logistics vehicles. Summary of the Invention

[0003] The purpose of the present invention is to overcome the shortcomings of the existing technology. The present invention provides a scheduling method and related devices for logistics transport vehicles, so that the planned target transport route is more accurate, avoiding large deviations from the actual drivable route, thereby ensuring that the target logistics transport vehicle can deliver the goods in time.

[0004] In order to solve the above technical problems, the present invention provides a method for dispatching logistics transport vehicles, which is applied to a logistics control center of a multi-level transportation network; the method comprises:

[0005] The logistics control center analyzes the priority of each cargo order based on cargo order data;

[0006] Based on cargo order data combined with load analysis, logistics transport vehicle scheduling analysis and order allocation are carried out to obtain the target order allocation plan for each target logistics transport vehicle;

[0007] Based on the current weather information and the weighted directed graph, the weather impact analysis of each road is carried out to obtain weather impact data;

[0008] Carry out traffic flow prediction for each road based on multimodal traffic data to obtain corresponding traffic flow prediction data;

[0009] Based on traffic flow forecast data and weather impact data, combined with the priority of each cargo order and the target order allocation plan, the transportation route of the target logistics transportation vehicle is planned to obtain the initial transportation route set;

[0010] The vehicle driving energy consumption and vehicle loss cost of each initial transportation route in the initial transportation route set are analyzed, the target transportation route is determined based on the vehicle driving energy consumption and vehicle loss cost, and the target transportation route and target order allocation plan are transmitted to the vehicle terminal of the target logistics transportation vehicle.

[0011] Optionally, analyzing the priority of each cargo order based on cargo order data includes:

[0012] Determine the customer level, order amount and remaining delivery period of each goods order based on the goods order data;

[0013] Determine the priority of each goods order based on customer level, order amount and remaining delivery period of the order.

[0014] Optionally, the scheduling analysis and order allocation of logistics transport vehicles based on cargo order data combined with load analysis to obtain a target order allocation plan for each target logistics transport vehicle includes:

[0015] Determine cargo weight based on cargo order data, perform scheduling analysis based on cargo order data, determine a number of target logistics transport vehicles, and determine an initial order allocation plan for each target logistics transport vehicle based on cargo weight;

[0016] Based on the initial order allocation plan, the weighing data of each vehicle part in each target logistics transport vehicle is obtained, and data association and load analysis are performed based on the weighing data of each vehicle part to obtain the load association data of each vehicle part;

[0017] The load distribution characteristics of each target logistics transport vehicle are determined based on the load correlation data of each vehicle part, and the initial order allocation plan is adjusted based on the load distribution characteristics to obtain the target order allocation plan for each target logistics transport vehicle.

[0018] Optionally, the weather impact analysis of each road traffic based on current weather information combined with a weighted directed graph to obtain weather impact data includes:

[0019] Each intersection in the road network is regarded as a node, the lines between adjacent intersections are regarded as edges, and a weighted directed graph is constructed based on the nodes and edges;

[0020] Based on current weather information, a weighted directed graph is used to analyze the water depth, visibility, and road slipperiness of each road, obtaining water depth data, visibility data, and road slipperiness data.

[0021] Based on the water depth data, visibility data and road slipperiness data, a weather impact analysis on the passage of each road is performed to obtain weather impact data.

[0022] Optionally, performing traffic flow prediction for each road based on multimodal traffic data to obtain corresponding traffic flow prediction data includes:

[0023] Preprocessing the multimodal traffic data of each road to obtain preprocessed multimodal traffic data, and extracting feature vectors from the preprocessed multimodal traffic data to obtain corresponding target feature vectors;

[0024] Based on the self-attention mechanism, several target feature vectors are fused to obtain a fused feature vector;

[0025] Based on the heterogeneous attention mechanism, the road traffic map and the traffic flow time series features generated by the traffic flow time series are aggregated to obtain the aggregation results;

[0026] Optimize the parameters of the traffic flow prediction model based on the aggregation results to obtain the optimized traffic flow prediction model;

[0027] The fused feature vector is input into the optimized traffic flow prediction model to predict the traffic flow of each road, and the corresponding traffic flow prediction data is obtained.

[0028] Optionally, the transportation route planning of the target logistics transport vehicle is performed based on the traffic flow forecast data and weather impact data in combination with the priority of each cargo order and the target order allocation plan to obtain an initial transportation route set, including:

[0029] Determine the path endpoint sequence of each target logistics transport vehicle based on the target order allocation plan and the priority of each cargo order, and determine the route set of each target logistics transport vehicle based on the path endpoint sequence;

[0030] Determine safe driving speeds for each road based on traffic flow forecast data and weather impact data;

[0031] The estimated driving time of each route in the route set is analyzed based on the safe driving speed of each road, and the initial transportation route set of each target logistics transportation vehicle is determined based on the estimated driving time.

[0032] Optionally, analyzing the vehicle driving energy consumption and vehicle loss cost of each initial transportation route in the initial transportation route set and determining the target transportation route based on the vehicle driving energy consumption and vehicle loss cost includes:

[0033] determining an accelerator pedal opening based on a safe driving speed on each road in each initial transport route, and determining a motor driving torque based on the accelerator pedal opening;

[0034] determining the motor power based on the motor drive torque and the motor speed, and determining the vehicle driving energy consumption for each initial transport route based on the motor power;

[0035] Analyze the loss rate and tolls required for the target logistics transport vehicle to travel along each corresponding initial transport route, and determine the vehicle loss cost for each initial transport route based on the loss rate and tolls;

[0036] The comprehensive cost of path travel is analyzed based on vehicle travel energy consumption and vehicle loss cost, and the target transport route of each target logistics transport vehicle is determined in the initial transport route set based on the comprehensive cost of path travel.

[0037] In addition, the present invention also provides a dispatching device for logistics transport vehicles, which is applied to a logistics control center of a multi-level transportation network; the device comprises:

[0038] Order priority analysis module: used by the logistics control center to analyze the priority of each cargo order based on cargo order data;

[0039] Order allocation module: used to perform scheduling analysis and order allocation for logistics transport vehicles based on cargo order data combined with load analysis, and obtain target order allocation plans for each target logistics transport vehicle;

[0040] Weather impact analysis module: used to analyze the weather impact of each road based on current weather information combined with a weighted directed graph to obtain weather impact data;

[0041] Traffic flow prediction module: used to predict the traffic flow of each road based on multimodal traffic data and obtain corresponding traffic flow prediction data;

[0042] Initial route planning module: This module is used to plan the transport routes of target logistics transport vehicles based on traffic flow forecast data and weather impact data, combined with the priority of each cargo order and the target order allocation plan, to obtain the initial transport route set;

[0043] Target route determination module: used to analyze the vehicle driving energy consumption and vehicle loss cost of each initial transportation route in the initial transportation route set, determine the target transportation route based on the vehicle driving energy consumption and vehicle loss cost, and transmit the target transportation route and target order allocation plan to the vehicle terminal of the target logistics transportation vehicle.

[0044] In addition, the present invention also provides an electronic device, which includes a processor and a memory, wherein the memory is used to store instructions, and the processor is used to call the instructions in the memory so that the electronic device executes the above-mentioned logistics transportation vehicle scheduling method.

[0045] In addition, the present invention also provides a computer-readable storage medium, which stores computer instructions. When the computer instructions are executed on an electronic device, the electronic device executes the above-mentioned method for scheduling logistics transportation vehicles.

[0046] In an embodiment of the present invention, scheduling analysis and order allocation for logistics transport vehicles are performed based on cargo order data combined with load analysis, which can effectively avoid the problem of cargo overload in logistics transport vehicles and improve the stability and safety of logistics transport vehicles. Weather impact analysis of each road traffic is performed based on current weather information combined with a weighted directed graph, effectively improving the reliability of weather impact analysis. Traffic flow prediction for each road based on multimodal traffic data can ensure the accuracy of the traffic flow prediction data obtained. Based on traffic flow prediction data and weather impact data, combined with the priority of each cargo order and the target order allocation plan, transportation route planning for the target logistics transport vehicle is performed to obtain an initial transportation route set. The vehicle driving energy consumption and vehicle loss cost of each initial transportation route in the initial transportation route set are analyzed to determine the target transportation route. Traffic flow, weather impact, vehicle driving energy consumption and vehicle loss cost are all taken into account in the transportation route planning, making the planned target transportation route more accurate and avoiding large deviations from the actual drivable route, thereby ensuring that the target logistics transport vehicle can deliver the goods in a timely manner. BRIEF DESCRIPTION OF THE DRAWINGS

[0047] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, 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. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0048] Figure 1 1 is a flow chart of a method for dispatching logistics transport vehicles in an embodiment of the present invention;

[0049] Figure 2 is a flow chart of a method for dispatching logistics transportation vehicles in another embodiment of the present invention;

[0050] Figure 3 Schematic diagram of the structure of a dispatching device for logistics transport vehicles in an embodiment of the present invention;

[0051] Figure 4 It is a schematic diagram of the structure of an electronic device in an embodiment of the present invention. DETAILED DESCRIPTION

[0052] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making any creative efforts shall fall within the scope of protection of the present invention.

[0053] Example 1

[0054] See also Figure 1 , Figure 1 : is a flow chart of a method for dispatching logistics transport vehicles in an embodiment of the present invention, the method being applied to a logistics control center of a multi-level transport network, the method comprising:

[0055] S11: The logistics control center analyzes the priority of each cargo order based on the cargo order data;

[0056] In the specific implementation process of the present invention, the priority of each cargo order is analyzed based on the cargo order data, including: determining the customer level, order amount and remaining delivery period of each cargo order based on the cargo order data; determining the priority of each cargo order based on the customer level, order amount and remaining delivery period of the order.

[0057] Specifically, each level of transportation network has its corresponding logistics control center, which is used to process logistics orders from transportation stations at all levels. For example, the first-level transportation network is a city-level transportation network, and its logistics control center is used to operate cargo orders from second-level transportation stations and out-of-city logistics transportation. The second-level transportation network can be a district-level transportation network, and its logistics control center is used to receive and transfer cargo orders from first-level transportation stations and third-level transportation stations. And so on, the processing of cargo orders at different levels can be realized through the logistics control center of the multi-level transportation network, thereby ensuring the orderly processing of cargo orders.

[0058] The logistics control center receives cargo order data, which includes customer information, order amount, delivery deadline, and cargo information for each cargo order. Based on the cargo order data, the center determines the customer rank, order amount, and remaining delivery deadline for each cargo order. The customer information determines the customer rank of each cargo order. The higher the customer rank, the higher the priority of the cargo order. The order amount affects the revenue and profit of the order, so the higher the order amount, the higher the priority. The shorter the remaining delivery deadline, the higher the priority of the order. The center prioritizes each cargo order based on the customer rank, order amount, and remaining delivery deadline. The priority of each cargo order is determined based on the customer rank, order amount, remaining delivery deadline, and their corresponding weight coefficients.

[0059] S12: Performing scheduling analysis and order allocation for logistics transport vehicles based on cargo order data combined with load analysis to obtain a target order allocation plan for each target logistics transport vehicle;

[0060] In the specific implementation process of the present invention, the scheduling analysis and order allocation of logistics transport vehicles based on cargo order data combined with load analysis are performed to obtain a target order allocation plan for each target logistics transport vehicle, including: determining the weight of the cargo based on the cargo order data, performing scheduling analysis based on the cargo order data, determining a number of target logistics transport vehicles, and determining an initial order allocation plan for each target logistics transport vehicle based on the cargo weight; obtaining weighing data of each vehicle part in each target logistics transport vehicle based on the initial order allocation plan, and performing data association and load analysis based on the weighing data of each vehicle part to obtain load association data of each vehicle part; determining the load distribution characteristics of each target logistics transport vehicle based on the load association data of each vehicle part, and adjusting the initial order allocation plan based on the load distribution characteristics to obtain a target order allocation plan for each target logistics transport vehicle.

[0061] Specifically, the cargo weight is determined based on the cargo order data, and scheduling analysis is performed based on the cargo order data, that is, the required number of logistics transport vehicles is determined according to the cargo quantity in the cargo order data, the vehicle type is determined according to the cargo type in the cargo order data, and the required number of target logistics transport vehicles is determined according to the required quantity and the required vehicle type. The initial order allocation plan for each target logistics transport vehicle is determined based on the cargo weight, and each type of cargo is evenly distributed to the corresponding type of logistics transport vehicles according to the cargo weight of each type of cargo, which is the initial order allocation plan. Based on the initial order allocation plan, the weighing data of each vehicle part in each target logistics transport vehicle is obtained, and the corresponding goods are allocated to each target logistics transport vehicle according to the initial order allocation plan for weighing testing. The target logistics transport vehicle is divided according to different components of the vehicle, such as the front, body and rear, to obtain several vehicle parts. The data of each vehicle part is collected through a piezoelectric weighing device to obtain the corresponding weighing data, and data association and load analysis are performed based on the weighing data of each vehicle part. The weighing data of each vehicle part is data-associated according to the timestamp of the weighing test, and the weighing data after data association are fused to obtain fused data. The fused data is load analyzed by machine learning technology, and the load conditions between different vehicle parts are associated to obtain load association data of each vehicle part. Based on the load association data of each vehicle part, the load distribution characteristics of each target logistics transport vehicle are determined, and the load association data of each vehicle part are input into the distribution characteristic data model for load distribution analysis to obtain the load distribution characteristics of each target logistics transport vehicle, such as the load concentration area, whether the load distribution is uniform, etc., and the initial order allocation plan is adjusted based on the load distribution characteristics. According to the load distribution characteristics of each target logistics transport vehicle, the target logistics transport vehicle with overload is determined, and for the target logistics transport vehicle with overload, the overload amount of its order goods is allocated to the non-overloaded vehicle, that is, the target order allocation plan for each target logistics transport vehicle is obtained.

[0062] S13: Analyze the weather impact on each road based on the current weather information and the weighted directed graph to obtain weather impact data;

[0063] In the specific implementation process of the present invention, the weather impact analysis on the passage of each road is performed based on the current weather information in combination with a weighted directed graph to obtain weather impact data, including: taking each intersection in the road network as a node, and the connecting lines between adjacent intersections as edges, and constructing a weighted directed graph based on the nodes and edges; based on the current weather information, using the weighted directed graph to perform water accumulation depth analysis, visibility analysis and road slipperiness analysis on each road to obtain water accumulation depth data, visibility data and road slipperiness data; based on the water accumulation depth data, visibility data and road slipperiness data, the weather impact analysis on the passage of each road is performed to obtain weather impact data.

[0064] Specifically, each intersection in the road network is treated as a node, the lines between adjacent intersections as edges, and the length of the edges sets the weight. A weighted directed graph is constructed based on the nodes, edges, and their weights. Based on current weather information, the weighted directed graph is used to analyze the water depth, visibility, and road slipperiness of each road. Current weather information, including rainfall, snowfall, fog density, and wind speed, is collected and input into the simulation model. The simulation model is used to perform simulation analysis based on rainfall and the weighted directed graph, outputting the water depth of the road. The simulation model is used to perform simulation analysis based on snowfall, rainfall, and the weighted directed graph, outputting the road slipperiness. The simulation model is used to perform simulation analysis based on fog density and the weighted directed graph, outputting the road visibility, thereby obtaining water depth data, visibility data, and road slipperiness data. Based on the water depth data, visibility data and road slipperiness data, a weather impact analysis on the passage of each road is performed, that is, the impact of the water depth data, visibility data and road slipperiness data of the current road on the passage of vehicles is analyzed, and the impact on the speed, road adhesion coefficient and slip rate of the passage of each road is analyzed, that is, the weather impact data is obtained.

[0065] S14: Predicting traffic flow on each road based on the multimodal traffic data to obtain corresponding traffic flow prediction data;

[0066] In the specific implementation process of the present invention, the traffic flow prediction of each road based on multimodal traffic data to obtain corresponding traffic flow prediction data includes: preprocessing the multimodal traffic data of each road to obtain preprocessed multimodal traffic data, and extracting feature vectors from the preprocessed multimodal traffic data to obtain corresponding target feature vectors; fusing the target feature vectors based on the self-attention mechanism to obtain a fused feature vector; aggregating the road traffic map and the traffic flow time series features generated by the traffic flow time series based on the heterogeneous attention mechanism to obtain an aggregation result; optimizing the parameters of the traffic flow prediction model based on the aggregation result to obtain an optimized traffic flow prediction model; inputting the fused feature vector into the optimized traffic flow prediction model to perform traffic flow prediction for each road to obtain corresponding traffic flow prediction data.

[0067] Specifically, multimodal traffic data for each road is preprocessed. Multimodal traffic data includes structured, semi-structured, and unstructured data. Structured data includes the number of vehicles, vehicle speed, and lane occupancy at each monitoring point. Semi-structured data includes vehicle Global Positioning System (GPS) data and user feedback data, including information on traffic accidents and congestion on each road. Unstructured data includes real-time video streams captured by cameras and social media data. Preprocessing of structured data includes data cleaning and standardization. Preprocessing of vehicle GPS data in semi-structured data includes smoothing to address missing data caused by network fluctuations. User feedback data is input as text and requires denoising. Preprocessing of real-time video streams in unstructured data includes denoising and image enhancement. Social media data is text data and requires denoising. The preprocessed multimodal traffic data is then subjected to feature vector extraction. Feature vectors are extracted from each data point in the multimodal traffic data using a deep neural network to obtain several corresponding target feature vectors. Based on the self-attention mechanism, several target feature vectors are fused. The core of the self-attention mechanism is to assign appropriate weights to each data to ensure that representative information is fully utilized. A query vector, key vector and value vector are generated for each target feature vector. The dot product attention is used to calculate the attention weights between each target feature vector through the query vector and the key vector. The attention weights are used to fuse the features of each target feature vector through the value vector to obtain a fused feature vector. This fused feature vector combines the effective information in multimodal traffic data. Based on the heterogeneous attention mechanism, the road traffic map and the traffic flow time series features generated by the traffic flow time series are aggregated. A target road node is set, all nodes connected to the target road node are collected, and a number of adjacent nodes are retained. The dynamic traffic flow of each node is obtained and marked in each road node to form a road traffic map. The traffic flow time series is the traffic flow data of each road node at each time point in the road traffic map. The traffic flow time series features of the traffic flow time series are extracted through a feature extraction network. At a selected time point, the spatial dependency of the adjacent nodes and their traffic data in the road traffic map is analyzed using the heterogeneous attention mechanism. The heterogeneous attention mechanism can be used to mine coarse-grained spatial information and dynamic temporal dependency. The attention score between the target road node and each adjacent node is calculated based on the spatial dependency. The updated spatiotemporal representation of the target road node is calculated based on the attention score. The updated spatiotemporal representation is transferred to the adjacent nodes. Based on the transferred result, the prediction value of the next time point is generated using a multi-layer perceptron. In this way, the aggregation of the road traffic map and traffic flow time series features is completed, and the aggregation result is obtained.Based on the aggregation results, the parameters of the traffic flow prediction model are optimized. The loss function is determined based on the predicted value in the aggregation results and the true value at the corresponding time point. The parameters of the traffic flow prediction model are reversely optimized based on the loss function. The traffic flow prediction model uses a long short-term memory network. The loss function is used to evaluate the model accuracy and guide subsequent parameter updates to achieve parameter optimization of the model and obtain an optimized traffic flow prediction model. The use of a long short-term memory network can capture the dependencies in traffic flow, which is more beneficial when dealing with complex and dynamic traffic environments and can generate more accurate traffic flow prediction results. The fused feature vector is input into the optimized traffic flow prediction model to predict the traffic flow of each road, that is, predict the traffic flow of each road and obtain corresponding traffic flow prediction data.

[0068] S15: Based on the traffic flow forecast data and weather impact data, combined with the priority of each cargo order and the target order allocation plan, the transportation route of the target logistics transportation vehicle is planned to obtain an initial transportation route set;

[0069] In the specific implementation process of the present invention, the transportation route planning of the target logistics transport vehicle is carried out based on the traffic flow forecast data and weather impact data in combination with the priority of each cargo order and the target order allocation plan to obtain an initial transportation route set, including: determining the path terminal sequence of each target logistics transport vehicle based on the target order allocation plan and the priority of each cargo order, and determining the route set of each target logistics transport vehicle based on the path terminal sequence; determining the safe driving speed of each road based on the traffic flow forecast data and weather impact data; analyzing the expected driving time of each route in the route set based on the safe driving speed of each road, and determining the initial transportation route set of each target logistics transport vehicle based on the expected driving time.

[0070] Specifically, the target logistics transport vehicle's route endpoint sequence is determined based on the target order allocation plan and the priority of each cargo order. The transport destinations are determined based on the cargo orders assigned to each target logistics transport vehicle. The order of transport destinations is determined based on the priority of each cargo order to form a route endpoint sequence. A route set for each target logistics transport vehicle is determined based on the route endpoint sequence. Several drivable routes from each target logistics transport vehicle to each transport destination are determined based on the route endpoint sequence to form a route set for each target logistics transport vehicle. The safe driving speed for each road is determined based on traffic flow forecast data and weather impact data, and the safe driving speed for each road is matched based on the traffic flow and weather impact data for each road. The estimated driving time of each route in the route set is analyzed based on the safe driving speed of each road. The initial driving time of each route is analyzed according to the safe driving speed and the distance of each route. At the same time, the estimated road congestion duration is analyzed through traffic flow prediction data. The estimated driving time of each road is determined based on the initial driving time and the estimated road congestion duration. The initial transport route set of each target logistics transport vehicle is determined based on the estimated driving time. Several routes with estimated driving times less than a preset threshold are selected from the route set as the initial transport route set of the target logistics transport vehicles.

[0071] S16: Analyze the vehicle driving energy consumption and vehicle loss cost of each initial transportation route in the initial transportation route set, determine the target transportation route based on the vehicle driving energy consumption and vehicle loss cost, and transmit the target transportation route and target order allocation plan to the vehicle terminal of the target logistics transportation vehicle.

[0072] In the specific implementation process of the present invention, the vehicle driving energy consumption and vehicle loss cost of each initial transport route in the initial transport route set are analyzed, and the target transport route is determined based on the vehicle driving energy consumption and vehicle loss cost, including: determining the accelerator pedal opening based on the safe driving speed of each road in each initial transport route, and determining the motor driving torque based on the accelerator pedal opening; determining the motor power based on the motor driving torque and the motor speed, and determining the vehicle driving energy consumption of each initial transport route based on the motor power; analyzing the loss rate and toll required for the target logistics transport vehicle to travel in the corresponding initial transport routes, and determining the vehicle loss cost of each initial transport route based on the loss rate and toll; analyzing the comprehensive cost of path travel based on the vehicle driving energy consumption and vehicle loss cost, and determining the target transport route of each target logistics transport vehicle in the initial transport route set based on the comprehensive cost of path travel.

[0073] Specifically, the accelerator pedal opening is determined based on the safe driving speed for each road in each initial transport route. The accelerator pedal opening is a percentage value reflecting the degree to which the accelerator pedal is depressed, and each value corresponds to a different driving speed. Therefore, the accelerator pedal opening can be directly determined based on the safe driving speed, and the motor drive torque can be determined based on the accelerator pedal opening. Since there is a corresponding relationship between the accelerator pedal opening and the motor drive torque, the motor drive torque can be determined by looking up the accelerator pedal opening. The motor power is determined based on the motor drive torque and the motor speed. Similarly, the motor speed of the vehicle can be determined by looking up the table using the safe driving speed. The motor drive torque is multiplied by the motor speed to obtain the motor power. The vehicle driving energy consumption for each initial transport route is determined based on the motor power. The motor power is integrated to obtain the driving energy consumption for each road. The driving energy consumption of all roads in each initial transport route is then statistically analyzed to obtain the vehicle driving energy consumption for each initial transport route. The loss rate and tolls required for target logistics transport vehicles to travel along each corresponding initial transport route are analyzed. The loss rate and tolls required for the logistics transport vehicles to travel along each road are obtained from a vehicle travel information database. The loss rate and tolls required for traveling along each initial transport route are determined based on the loss rate and tolls for all roads. The vehicle loss cost for each initial transport route is determined based on the loss rate and tolls. The vehicle loss cost for each initial transport route is determined based on the loss rate and tolls combined with their corresponding weight coefficients. A comprehensive route travel cost is analyzed based on vehicle travel energy consumption and vehicle loss cost. The comprehensive route travel cost is calculated based on the vehicle travel energy consumption and vehicle loss cost and their corresponding weight coefficients. A target transport route is determined for each target logistics transport vehicle from the set of initial transport routes based on the comprehensive route travel cost. The route with the lowest comprehensive route travel cost from the set of initial transport routes is selected as the target transport route for the target logistics transport vehicle. The target transport route and target order allocation plan are transmitted to the vehicle terminal of the target logistics transport vehicle. The driver of each target logistics transport vehicle loads the cargo according to the target order allocation plan and transports the cargo to the corresponding destination along the target transport route.

[0074] In an embodiment of the present invention, scheduling analysis and order allocation for logistics transport vehicles are performed based on cargo order data combined with load analysis, which can effectively avoid the problem of cargo overload in logistics transport vehicles and improve the stability and safety of logistics transport vehicles. Weather impact analysis of each road traffic is performed based on current weather information combined with a weighted directed graph, effectively improving the reliability of weather impact analysis. Traffic flow prediction for each road based on multimodal traffic data can ensure the accuracy of the traffic flow prediction data obtained. Based on traffic flow prediction data and weather impact data, combined with the priority of each cargo order and the target order allocation plan, transportation route planning for the target logistics transport vehicle is performed to obtain an initial transportation route set. The vehicle driving energy consumption and vehicle loss cost of each initial transportation route in the initial transportation route set are analyzed to determine the target transportation route. Traffic flow, weather impact, vehicle driving energy consumption and vehicle loss cost are all taken into account in the transportation route planning, making the planned target transportation route more accurate and avoiding large deviations from the actual drivable route, thereby ensuring that the target logistics transport vehicle can deliver the goods in a timely manner.

[0075] Example 2

[0076] See also Figure 2 , Figure 2 FIG. 1 is a flow chart of a method for dispatching logistics transport vehicles in another embodiment of the present invention, the method being applied to a logistics control center of a multi-level transport network, the method comprising:

[0077] S201: The logistics control center analyzes the priority of each cargo order based on the cargo order data;

[0078] S202: Determine the cargo weight based on the cargo order data, perform scheduling analysis based on the cargo order data, determine a number of target logistics transport vehicles, and determine an initial order allocation plan for each target logistics transport vehicle based on the cargo weight;

[0079] S203: Obtaining weighing data of each vehicle part in each target logistics transport vehicle based on the initial order allocation plan, and performing data association and load analysis based on the weighing data of each vehicle part to obtain load association data of each vehicle part;

[0080] S204: Determine the load distribution characteristics of each target logistics transport vehicle based on the load association data of each vehicle part, and adjust the initial order allocation plan based on the load distribution characteristics to obtain a target order allocation plan for each target logistics transport vehicle;

[0081] S205: Analyzing the weather impact on each road based on the current weather information and the weighted directed graph to obtain weather impact data;

[0082] S206: Predicting traffic flow on each road based on the multimodal traffic data to obtain corresponding traffic flow prediction data;

[0083] S207: Planning the transport routes of target logistics transport vehicles based on the traffic flow forecast data and weather impact data in combination with the priorities of each cargo order and the target order allocation plan to obtain an initial transport route set;

[0084] S208: Analyze the vehicle driving energy consumption and vehicle loss cost of each initial transportation route in the initial transportation route set, determine the target transportation route based on the vehicle driving energy consumption and vehicle loss cost, and transmit the target transportation route and target order allocation plan to the vehicle terminal of the target logistics transportation vehicle.

[0085] In an embodiment of the present invention, scheduling analysis and order allocation for logistics transport vehicles are performed based on cargo order data combined with load analysis, which can effectively avoid the problem of cargo overload in logistics transport vehicles and improve the stability and safety of logistics transport vehicles. Weather impact analysis of each road traffic is performed based on current weather information combined with a weighted directed graph, effectively improving the reliability of weather impact analysis. Traffic flow prediction for each road based on multimodal traffic data can ensure the accuracy of the traffic flow prediction data obtained. Based on traffic flow prediction data and weather impact data, combined with the priority of each cargo order and the target order allocation plan, transportation route planning for the target logistics transport vehicle is performed to obtain an initial transportation route set. The vehicle driving energy consumption and vehicle loss cost of each initial transportation route in the initial transportation route set are analyzed to determine the target transportation route. Traffic flow, weather impact, vehicle driving energy consumption and vehicle loss cost are all taken into account in the transportation route planning, making the planned target transportation route more accurate and avoiding large deviations from the actual drivable route, thereby ensuring that the target logistics transport vehicle can deliver the goods in a timely manner.

[0086] Example 3

[0087] See also Figure 3 , Figure 3 : This is a schematic diagram of the structure of a dispatching device for logistics transport vehicles in an embodiment of the present invention. The device is applied to a logistics control center of a multi-level transportation network, and the device includes:

[0088] Order priority analysis module 31: used by the logistics control center to analyze the priority of each cargo order based on cargo order data;

[0089] Order allocation module 32: used to perform scheduling analysis and order allocation for logistics transport vehicles based on cargo order data combined with load analysis, and obtain target order allocation plans for each target logistics transport vehicle;

[0090] Weather impact analysis module 33: used to analyze the weather impact of each road based on current weather information combined with a weighted directed graph to obtain weather impact data;

[0091] Traffic flow prediction module 34: used to predict the traffic flow of each road based on multimodal traffic data and obtain corresponding traffic flow prediction data;

[0092] Initial route planning module 35: used to plan the transport routes of target logistics transport vehicles based on traffic flow forecast data and weather impact data combined with the priority of each cargo order and the target order allocation plan to obtain an initial transport route set;

[0093] Target route determination module 36: used to analyze the vehicle driving energy consumption and vehicle loss cost of each initial transportation route in the initial transportation route set, determine the target transportation route based on the vehicle driving energy consumption and vehicle loss cost, and transmit the target transportation route and target order allocation plan to the vehicle terminal of the target logistics transportation vehicle.

[0094] In the specific implementation process of the present invention, the specific implementation method of the device item can refer to the implementation method of the above-mentioned method item, which will not be repeated here.

[0095] In an embodiment of the present invention, scheduling analysis and order allocation for logistics transport vehicles are performed based on cargo order data combined with load analysis, which can effectively avoid the problem of cargo overload in logistics transport vehicles and improve the stability and safety of logistics transport vehicles. Weather impact analysis of each road traffic is performed based on current weather information combined with a weighted directed graph, effectively improving the reliability of weather impact analysis. Traffic flow prediction for each road based on multimodal traffic data can ensure the accuracy of the traffic flow prediction data obtained. Based on traffic flow prediction data and weather impact data, combined with the priority of each cargo order and the target order allocation plan, transportation route planning for the target logistics transport vehicle is performed to obtain an initial transportation route set. The vehicle driving energy consumption and vehicle loss cost of each initial transportation route in the initial transportation route set are analyzed to determine the target transportation route. Traffic flow, weather impact, vehicle driving energy consumption and vehicle loss cost are all taken into account in the transportation route planning, making the planned target transportation route more accurate and avoiding large deviations from the actual drivable route, thereby ensuring that the target logistics transport vehicle can deliver the goods in a timely manner.

[0096] An embodiment of the present invention provides a computer-readable storage medium, on which a computer program is stored. When the program is executed by a processor, the method for dispatching logistics transportation vehicles of any of the above embodiments is implemented. The computer-readable storage medium includes, but is not limited to, any type of disk (including floppy disks, hard disks, optical disks, CD-ROMs, and magneto-optical disks), ROM (Read-Only Memory), RAM (Random Access Memory), EPROM (Erasable Programmable Read-Only Memory), EEPROM (Electrically Erasable Programmable Read-Only Memory), flash memory, magnetic cards, or optical cards. In other words, the storage device includes any medium that can be used by a device (e.g., a computer, a mobile phone) to store or transmit information in a readable form, which can be a read-only memory, a disk, or an optical disk, etc.

[0097] Example 4

[0098] See also Figure 4 , Figure 4 It is a schematic diagram of the structure of an electronic device in an embodiment of the present invention.

[0099] The embodiment of the present invention further provides an electronic device, such as Figure 4 As shown, the electronic device includes a memory 41, a processor 43, and a computer program 42 stored in the memory 41 and executable on the processor 43. It will be understood by those skilled in the art that Figure 3The electronic devices shown do not constitute a limitation on all devices and may include more or fewer components than shown, or combinations of certain components. The memory 41 can be used to store the computer program 42 and various functional modules, and the processor 43 runs the computer program 42 stored in the memory 41, thereby executing various functional applications and data processing of the device. The memory can be internal memory or external memory, or include both internal memory and external memory. The internal memory can include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM), flash memory, or random access memory. The external memory can include a hard disk, floppy disk, ZIP disk, USB flash drive, magnetic tape, etc. The processor 43 can be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor may be a microprocessor, a single-chip microcomputer, or processor 43, or any conventional processor. The processor and memory disclosed in the present invention include but are not limited to these types of processors and memories. The processor and memory disclosed in the present invention are only examples and not limitations.

[0100] As an embodiment, the electronic device includes: one or more processors 43, a memory 41, and one or more computer programs 42, wherein the one or more computer programs 42 are stored in the memory 41 and are configured to be executed by the one or more processors 43, and the one or more computer programs 42 are configured to execute the scheduling method for logistics transportation vehicles in any of the above-mentioned embodiments. For the specific implementation process, please refer to the above-mentioned embodiments and will not be repeated here.

[0101] In an embodiment of the present invention, scheduling analysis and order allocation for logistics transport vehicles are performed based on cargo order data combined with load analysis, which can effectively avoid the problem of cargo overload in logistics transport vehicles and improve the stability and safety of logistics transport vehicles. Weather impact analysis of each road traffic is performed based on current weather information combined with a weighted directed graph, effectively improving the reliability of weather impact analysis. Traffic flow prediction for each road based on multimodal traffic data can ensure the accuracy of the traffic flow prediction data obtained. Based on traffic flow prediction data and weather impact data, combined with the priority of each cargo order and the target order allocation plan, transportation route planning for the target logistics transport vehicle is performed to obtain an initial transportation route set. The vehicle driving energy consumption and vehicle loss cost of each initial transportation route in the initial transportation route set are analyzed to determine the target transportation route. Traffic flow, weather impact, vehicle driving energy consumption and vehicle loss cost are all taken into account in the transportation route planning, making the planned target transportation route more accurate and avoiding large deviations from the actual drivable route, thereby ensuring that the target logistics transport vehicle can deliver the goods in a timely manner.

[0102] In addition, the above is a detailed introduction to a scheduling method and related devices for logistics transportation vehicles provided by an embodiment of the present invention. Specific examples are used herein to illustrate the principles and implementation methods of the present invention. The description of the above embodiments is only used to help understand the method of the present invention and its core idea. At the same time, for general technical personnel in this field, according to the ideas of the present invention, there will be changes in the specific implementation methods and application scopes. In summary, the content of this specification should not be understood as limiting the present invention.

Claims

1. A method for dispatching logistics transport vehicles, characterized in that: The method is applied to a logistics control center of a multi-level transportation network; the method comprises: The logistics control center analyzes the priority of each cargo order based on cargo order data; Based on cargo order data combined with load analysis, logistics transport vehicle scheduling analysis and order allocation are carried out to obtain the target order allocation plan for each target logistics transport vehicle; Based on the current weather information and the weighted directed graph, the weather impact analysis of each road is carried out to obtain weather impact data; Predicting traffic flow on each road based on multimodal traffic data to obtain corresponding traffic flow prediction data; Based on traffic flow forecast data and weather impact data, combined with the priority of each cargo order and the target order allocation plan, the transportation route of the target logistics transportation vehicle is planned to obtain the initial transportation route set; The vehicle driving energy consumption and vehicle loss cost of each initial transportation route in the initial transportation route set are analyzed, the target transportation route is determined based on the vehicle driving energy consumption and vehicle loss cost, and the target transportation route and target order allocation plan are transmitted to the vehicle terminal of the target logistics transportation vehicle.

2. The method for dispatching logistics transport vehicles according to claim 1, characterized in that: Analyzing the priority of each cargo order based on cargo order data includes: Determine the customer level, order amount and remaining delivery period of each goods order based on the goods order data; Determine the priority of each goods order based on customer level, order amount and remaining delivery period of the order.

3. The method for dispatching logistics transport vehicles according to claim 1, characterized in that: The scheduling analysis and order allocation of logistics transport vehicles based on cargo order data combined with load analysis to obtain a target order allocation plan for each target logistics transport vehicle includes: Determine cargo weight based on cargo order data, perform scheduling analysis based on cargo order data, determine a number of target logistics transport vehicles, and determine an initial order allocation plan for each target logistics transport vehicle based on cargo weight; Based on the initial order allocation plan, the weighing data of each vehicle part in each target logistics transport vehicle is obtained, and data association and load analysis are performed based on the weighing data of each vehicle part to obtain the load association data of each vehicle part; The load distribution characteristics of each target logistics transport vehicle are determined based on the load correlation data of each vehicle part, and the initial order allocation plan is adjusted based on the load distribution characteristics to obtain the target order allocation plan for each target logistics transport vehicle.

4. The method for dispatching logistics transport vehicles according to claim 1, characterized in that: The weather impact analysis of each road traffic based on current weather information combined with a weighted directed graph to obtain weather impact data includes: Each intersection in the road network is regarded as a node, the lines between adjacent intersections are regarded as edges, and a weighted directed graph is constructed based on the nodes and edges; Based on current weather information, a weighted directed graph is used to analyze the water depth, visibility, and road slipperiness of each road, obtaining water depth data, visibility data, and road slipperiness data. Based on the water depth data, visibility data and road slipperiness data, a weather impact analysis on the passage of each road is performed to obtain weather impact data.

5. The method for dispatching logistics transportation vehicles according to claim 1, characterized in that: The traffic flow prediction of each road based on the multimodal traffic data to obtain corresponding traffic flow prediction data includes: Preprocessing the multimodal traffic data of each road to obtain preprocessed multimodal traffic data, and extracting feature vectors from the preprocessed multimodal traffic data to obtain corresponding target feature vectors; Based on the self-attention mechanism, several target feature vectors are fused to obtain a fused feature vector; Based on the heterogeneous attention mechanism, the road traffic map and the traffic flow time series features generated by the traffic flow time series are aggregated to obtain the aggregation results; Optimize the parameters of the traffic flow prediction model based on the aggregation results to obtain the optimized traffic flow prediction model; The fused feature vector is input into the optimized traffic flow prediction model to predict the traffic flow of each road, and the corresponding traffic flow prediction data is obtained.

6. The method for dispatching logistics transport vehicles according to claim 1, characterized in that: The transportation route planning of the target logistics transport vehicle is performed based on the traffic flow forecast data and weather impact data in combination with the priority of each cargo order and the target order allocation plan to obtain an initial transportation route set, including: Determine the path endpoint sequence of each target logistics transport vehicle based on the target order allocation plan and the priority of each cargo order, and determine the route set of each target logistics transport vehicle based on the path endpoint sequence; Determine safe driving speeds for each road based on traffic flow forecast data and weather impact data; The estimated travel time of each route in the route set is analyzed based on the safe travel speed of each road, and the initial transport route set of each target logistics transport vehicle is determined based on the estimated travel time.

7. The method for dispatching logistics transportation vehicles according to claim 1, characterized in that: The analyzing the vehicle driving energy consumption and vehicle loss cost of each initial transportation route in the initial transportation route set and determining the target transportation route based on the vehicle driving energy consumption and vehicle loss cost includes: determining an accelerator pedal opening based on a safe driving speed on each road in each initial transport route, and determining a motor driving torque based on the accelerator pedal opening; determining the motor power based on the motor drive torque and the motor speed, and determining the vehicle driving energy consumption for each initial transport route based on the motor power; Analyze the loss rate and tolls required for the target logistics transport vehicle to travel along each corresponding initial transport route, and determine the vehicle loss cost for each initial transport route based on the loss rate and tolls; The comprehensive cost of path travel is analyzed based on vehicle travel energy consumption and vehicle loss cost, and the target transport route of each target logistics transport vehicle is determined in the initial transport route set based on the comprehensive cost of path travel.

8. A dispatching device for logistics transport vehicles, characterized in that: Applicable to a logistics control center of a multi-level transportation network; the device comprises: Order priority analysis module: used by the logistics control center to analyze the priority of each cargo order based on cargo order data; Order allocation module: used to perform scheduling analysis and order allocation for logistics transport vehicles based on cargo order data combined with load analysis, and obtain target order allocation plans for each target logistics transport vehicle; Weather impact analysis module: used to analyze the weather impact of each road based on current weather information combined with a weighted directed graph to obtain weather impact data; Traffic flow prediction module: used to predict the traffic flow of each road based on multimodal traffic data and obtain corresponding traffic flow prediction data; Initial route planning module: This module is used to plan the transport routes of target logistics transport vehicles based on traffic flow forecast data and weather impact data, combined with the priority of each cargo order and the target order allocation plan, to obtain the initial transport route set; Target route determination module: used to analyze the vehicle driving energy consumption and vehicle loss cost of each initial transportation route in the initial transportation route set, determine the target transportation route based on the vehicle driving energy consumption and vehicle loss cost, and transmit the target transportation route and target order allocation plan to the vehicle terminal of the target logistics transportation vehicle.

9. An electronic device comprising a processor and a memory, characterized in that: The memory is used to store instructions, and the processor is used to call the instructions in the memory so that the electronic device executes the scheduling method for logistics transportation vehicles as described in any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that The computer-readable storage medium stores computer instructions, and when the computer instructions are executed on an electronic device, the electronic device executes the method for dispatching logistics transportation vehicles according to any one of claims 1 to 7.

Images