Vehicle transportation management system and method based on digital technology

By integrating vehicle monitoring and intelligent scheduling modules in the vehicle transportation management system, combining energy consumption models and driving efficiency scores, and dynamically adjusting transportation paths, scheduling conflicts and energy planning problems in the existing system are solved, and transportation efficiency and safety are improved.

CN118941186AInactive Publication Date: 2024-11-12JIANGSU LINGHAO NETWORK TECH CO LTD +1

Patent Information

Application Number
CN202411428454.9
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-10-14
Publication Date
2024-11-12
Estimated Expiration
Not applicable · inactive patent

AI Technical Summary

Technical Problem

Existing vehicle transportation management systems are prone to scheduling conflicts and uneven resource allocation when dealing with large-scale, high-concurrent transportation tasks, and it is difficult to plan intelligent routes based on the remaining power and the availability of charging facilities, resulting in inefficient mid-stop or power exhaustion. risk.

Method used

A vehicle transportation management system based on digital technology was designed, integrating four functional modules: vehicle monitoring, intelligent scheduling, cargo management and reporting generation. Through real-time monitoring of energy status, intelligent early warning and supply, optimized task allocation and path planning, combined with vehicles Energy consumption model, driving efficiency score and supply station distribution, dynamically adjust transportation paths to avoid energy shortages.

Benefits of technology

It effectively avoids scheduling conflicts and uneven resource allocation, improves transportation efficiency, reduces operating costs, and reduces the risk of inefficient stops or power exhaustion, ensuring the smooth progress of transportation tasks.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118941186A_ABST
    Figure CN118941186A_ABST
Patent Text Reader

Abstract

The invention belongs to the field of vehicle transportation management, and particularly relates to a vehicle transportation management system and method based on the digital technology, the system integrates four functional modules of vehicle monitoring, intelligent scheduling, cargo management and report generation, the intelligent scheduling module optimizes task allocation and path planning and reduces empty driving, the cargo management module strictly monitors transportation tracks and cargo states and guarantees safety, and the report generation module periodically evaluates vehicle states and provides maintenance suggestions. Through accurate data analysis and intelligent decision, the transportation efficiency is remarkably improved, the operation cost is reduced, and the system is suitable for large-scale popularization and application. And the safety and reliability of cargo transportation are ensured.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The invention belongs to the field of vehicle transportation management, and specifically relates to a vehicle transportation management system and method based on digital technology. Background Art

[0002] With the rapid development of the logistics industry, vehicle transportation management faces increasingly complex challenges, especially in intelligent scheduling and route optimization. Traditional vehicle scheduling and route planning methods often rely on static data and preset rules, which are incapable of dealing with dynamically changing traffic conditions, sudden transportation needs, or unexpected vehicle failures. In addition, with the increasing awareness of environmental protection and the popularization of new energy vehicles, how to effectively manage and replenish vehicle energy while ensuring transportation efficiency and avoiding unnecessary waiting time due to insufficient energy has become a key issue that needs to be solved.

[0003] For example, the Chinese patent application with publication number CN113592400A discloses a logistics and transportation management system for digital application information collection, including a system management unit, a user management unit, an order management unit, an audit management unit, a content management unit, and a distributed data processing unit. This logistics and transportation management system for digital application information collection manages and tracks the data generated by users, vehicles, bank cards, drivers, and orders, as well as customers, orders, inventory, customs clearance, distribution, transportation, etc., and optimizes the work of each link through intelligent algorithms, completes the maintenance and audit of information, and meets the needs of enterprise information construction.

[0004] For example, a Chinese patent application with publication number CN114386846A discloses an earthwork transportation comprehensive management platform and management method based on an intelligent brain, including: receiving earthwork request information from a construction unit; obtaining situation information about a processing unit; matching and associating the construction unit with the processing unit based on the earthwork request information and the situation information, and generating associated information; receiving matching vehicle information selected by the construction unit; generating a task order based on the earthwork request information, the associated information and the matching vehicle information, and sending the task order to the matching vehicle based on the matching vehicle information; and monitoring the matching vehicle based on the task order until the matching vehicle completes the task.

[0005] The above existing technologies have the following problems: 1) When dealing with large-scale, high-concurrency transportation tasks, scheduling conflicts or uneven resource allocation and long vehicle waiting times often occur; 2) How to perform intelligent route planning based on remaining power, expected energy consumption and the availability of charging facilities along the way to avoid inefficient stops or the risk of running out of power is a function that is generally lacking in existing systems; In order to solve the above problems, the present invention provides a vehicle transportation management system and method based on digital technology. Summary of the invention

[0006] In view of the shortcomings of the prior art, the present invention proposes a vehicle transportation management system and method based on digital technology. The system integrates four major functional modules: vehicle monitoring, intelligent scheduling, cargo management and report generation. The vehicle monitoring module monitors the energy status in real time and intelligently warns of supply needs. The intelligent scheduling module optimizes task allocation and path planning to reduce empty driving. The cargo management module strictly monitors the transportation trajectory and cargo status to ensure safety. The report generation module regularly evaluates the vehicle status and provides maintenance suggestions. The present invention significantly improves transportation efficiency, reduces operating costs, and ensures the safety and reliability of cargo transportation through precise data analysis and intelligent decision-making.

[0007] To achieve the above object, the present invention provides the following technical solutions:

[0008] A vehicle transportation management system based on digital technology, comprising: an intelligent dispatching module, a vehicle monitoring module and a report generating module;

[0009] The vehicle monitoring module includes a vehicle monitoring unit and a consumption prediction and early warning unit;

[0010] The vehicle monitoring unit is used to monitor and obtain the energy reserve status, vehicle operation status and vehicle detection data of the transport vehicle in the process of transport or non-transportation in real time; the consumption prediction and early warning unit is used to build a vehicle energy consumption model, and combine the energy reserve status, vehicle operation status and the path length of the corresponding task to predict the path length of the vehicle within the normal driving time and the number of times the corresponding task planning path needs to be replenished under the current energy reserve status. At the same time, according to the predicted path length within the normal driving time and the actual path length of the transport vehicle corresponding to the task, an energy shortage early warning is issued;

[0011] The intelligent scheduling module includes a task allocation unit; the task allocation unit is used to allocate corresponding tasks to each transport vehicle through an intelligent allocation algorithm according to the attributes of the assigned tasks, the energy reserve status, the transport vehicle status evaluation score and the transport vehicle waiting time;

[0012] The report generation module includes a vehicle status detection unit; the vehicle status detection unit is used to perform real-time or periodic status score evaluation on the transport vehicle based on the acquired vehicle detection data through a comprehensive fuzzy evaluation algorithm, obtain the status evaluation score, and determine the vehicle's operating capability based on the status evaluation score, and feed the determination result back to the task allocation unit.

[0013] Specifically, the vehicle operation status includes vehicle load, road condition and driving efficiency score; the intelligent scheduling module also includes a path planning unit; the consumption prediction and early warning unit predicts the path length of the vehicle within the normal driving time under the current energy reserve state through the vehicle energy consumption model. The specific steps include:

[0014] A1. Obtain historical energy reserve status, vehicle load, road condition, driving efficiency score and energy consumption data per unit length of N types of transport vehicles, and pre-process the acquired data;

[0015] A2: Use support vector machine to build a vehicle energy consumption model, and use the preprocessed data in A1 to build the vehicle energy consumption model input sequence ,in, It indicates the energy reserve status of the nth type of transport vehicle monitored at the current time t. It indicates that the load status data of the nth type of transport vehicle is monitored at the current time t. Indicates the road status data of the transport vehicle monitored at the current time t. It indicates the driving efficiency score corresponding to the nth type of transport vehicle monitored at the current time t. It indicates the amount of energy consumed by the transport vehicle to reach the nearest supply station at the current time t. represents the reserved energy threshold;

[0016] A3. Input the obtained input sequence X into the vehicle energy consumption model for training, and fit the corresponding path length formula within the normal driving time, which is: ,in It represents the path length of the nth type of transport vehicle within the normal driving time at the current moment. The function representing the energy consumption per unit distance of the nth type of transport vehicle;

[0017] A4. The trained vehicle energy consumption model is built into the consumption prediction and early warning unit. According to the real-time monitored transport vehicle energy reserve status and vehicle operation status data, the corresponding transport vehicle’s energy consumption is calculated in real time. ;

[0018] A5. According to the obtained The path planning unit assigns the total length of the task-planned path to the corresponding transport vehicle, and calculates the number of corresponding replenishments for the transport vehicle.

[0019] Specifically, the specific steps for obtaining the driving efficiency score in A2 include:

[0020] A21. Collect and obtain the driving status data of the nth type of transport vehicle per unit length in real time through the on-board sensors of the transport vehicle, including acceleration, braking action, driving speed, idling time and the total number of vehicles per unit area;

[0021] A22. Construct driving efficiency evaluation indicators based on the acquired data, including acceleration smoothness, braking frequency, average speed, average idling time and road congestion;

[0022] A23. Based on the acquired driving efficiency evaluation index, a scoring formula for the corresponding evaluation index is constructed. Based on the acquired scoring formula for the evaluation index and the real-time acquired driving status data per unit length of the transport vehicle, the corresponding evaluation index score is calculated, which is specifically:

[0023]

[0024] in, represents the acceleration smoothness score of the nth type of transport vehicle, K represents the average number of accelerations of the nth type of transport vehicle per unit length, represents the acceleration value of the transport vehicle at the kth acceleration, represents the braking frequency score of the nth type of transport vehicle, M represents the average number of braking times of the nth type of transport vehicle per unit length, Indicates the intensity of the mth braking of the transport vehicle; represents the average speed score of the nth type of transport vehicle, It represents the average speed of the nth type of transport vehicle per unit length. and represents the maximum and minimum energy-saving speed interval thresholds of the nth type of transport vehicle, represents the average idling time score of the nth type of transport vehicle, It represents the average idling time of the nth type of transport vehicle within a unit length. It represents the total driving time of the nth type of transport vehicle within a unit length; represents the congestion degree of the transport vehicle during its travel at time t, It represents the total number of vehicles in the unit area S corresponding to the transport vehicles at time t;

[0025] A24. Based on the index scores obtained in A23, the driving efficiency score of the nth type of transport vehicle is calculated using a weighted strategy. , the weighted strategy is as follows: ,in, and Indicates the weighting coefficient of the corresponding indicator score.

[0026] Specifically, the specific steps of the consumption forecasting and warning unit for carrying out energy shortage warning include:

[0027] A6. Assume that the overall path length of the transport vehicle A corresponding to the task to be performed , the A4 real-time calculation results are and For comparison, if No warning will be given when When , assuming The corresponding path includes P supply stations, and the supply stations are divided according to their distance from the starting point of the task. Divided into P+1 driving intervals;

[0028] A7. The vehicle monitoring unit monitors the energy reserve status of the transport vehicle in P+1 driving intervals in real time. When the transport vehicle reaches the pth driving interval, the energy reserve status corresponding to the pth driving interval is - + When the energy shortage warning is issued to the transport vehicle A;

[0029] A8. When the transport vehicle reaches the pth driving interval, the corresponding energy storage state is - > + When , no warning is issued for the transport vehicle traveling in the pth driving interval;

[0030] A9. Repeat steps A7 and A8 to make corresponding warning judgments for the remaining driving range, and issue energy shortage warnings based on the warning judgment results.

[0031] Specifically, the specific steps performed by the task allocation unit include:

[0032] B1. Assume that there are U pending tasks and V transport vehicles at the current time. Set the uth pending task to be assigned to the task at the time. To the latest time point specified in the task attributes for task completion The window length is used as the priority of the corresponding task to be executed , specifically , set the vth transport vehicle to correspond to the length of the waiting time window As the priority of corresponding transport vehicles , specifically ;

[0033] B2, build a task allocation model through simulated annealing algorithm, using the obtained task and vehicle priorities, and the corresponding transport vehicle calculated by A4 The objective function of the task allocation model is constructed based on the number of replenishment , the objective function is , ;

[0034] in, represents the matching degree between the u-th task and the v-th transport vehicle, represents the task completion time after the v-th transport vehicle is assigned to task u; It represents the minimum sum of time required for V transport vehicles to complete U tasks to be performed;

[0035] B3. Train the constructed task allocation model using the objective function and the task attribute data, vehicle attribute data and vehicle operation status data obtained through monitoring, and obtain the trained task allocation model, so that the probability of the vehicle with the highest priority among the V transport vehicles being assigned to the task is maximized when the U tasks to be executed are completed in the shortest time;

[0036] B4. The trained task allocation model is built into the task allocation unit, and the corresponding tasks are allocated according to the task attribute data, vehicle attribute data and vehicle operation status data acquired in real time.

[0037] Specifically, the vehicle transportation management system further includes a report generation module, which further includes a vehicle status detection unit; the vehicle status detection unit is used to perform a real-time or periodic status score evaluation on the transport vehicle according to the acquired vehicle detection data through a comprehensive fuzzy evaluation algorithm, and to determine the vehicle operation capability according to the score, and to feed back the determination result to the task allocation unit;

[0038] The specific steps for obtaining the matching degree between the u-th task and the v-th transport vehicle in B2 include:

[0039] B21, based on the obtained tasks and vehicle priorities, and A4 calculated the corresponding transport vehicles The number of replenishment and the status assessment score of the corresponding transport vehicle Construct an input sequence and use the support vector machine to build a task matching model. Input the acquired input sequence into the task matching model for training, and fit the task matching model formula. The specific formula is:

[0040]

[0041] Among them, max represents the maximum value, represents the matching degree between the u-th task and the v-th transport vehicle, represents the number of times transport vehicle v needs to be replenished to perform task u, represents the status evaluation score of the vth transport vehicle obtained by the vehicle status detection unit, Represents the weight coefficient of task priority and vehicle priority, Indicates the weight coefficient of the impact of the number of replenishment times on the matching degree, is a constant value;

[0042] B22. The trained task matching model is built into the task allocation unit. The matching degree between the task u to be assigned and the transport vehicle v is calculated based on the task attribute data, the transport vehicle usage status data and the evaluation score acquired in real time. The calculated matching degree is fed back to the task allocation model to allocate the corresponding task.

[0043] Specifically, the specific steps of the vehicle state detection unit include:

[0044] C1. Use the mechanical performance, safety performance, electronic system performance, maintenance and servicing status, and energy efficiency of transport vehicles in the acquired vehicle inspection data to construct a first-level assessment factor set for transport vehicles;

[0045] C2. Construct the corresponding secondary evaluation factor set and evaluation index set based on the obtained primary evaluation factor set of the transport vehicle, and input the obtained primary evaluation factor set, secondary evaluation factor set and evaluation index set into the comprehensive fuzzy algorithm to score the transport vehicle status and obtain the status evaluation score of the vth transport vehicle. ;

[0046] C3. Set comprehensive scoring threshold and ,when When , no task is assigned to the vth transport vehicle. When the vth transport vehicle can only participate in satisfying The allocation of tasks to be executed according to the conditions, when When the vth transport vehicle can participate in the allocation of all tasks to be performed; Represents the median priority of all tasks to be executed;

[0047] C4, the status evaluation score of the corresponding v-th transport vehicle The results obtained in C3 are fed back to the task allocation unit to adjust the task matching allocation process.

[0048] A vehicle transportation management method based on digital technology, comprising the following steps:

[0049] S1. Obtaining the energy storage status, vehicle operation status and vehicle detection data of the transport vehicle, and preprocessing the acquired data;

[0050] S2. Based on the pre-processed energy reserve state and vehicle operation state, the vehicle energy consumption model is used to predict the path length of the transport vehicle within the normal driving time under the current energy reserve and the number of replenishment times required for the corresponding task planning path. At the same time, the vehicle detection data is input into the vehicle state detection unit to obtain the state evaluation score of the corresponding transport vehicle;

[0051] S3. According to the output results of the vehicle energy consumption model, the vehicle status evaluation score and the task attribute data, the task matching model is used to assign the corresponding task to be performed to each transport vehicle, and according to the assigned task attributes and the operating status data of the corresponding transport vehicle, the path planning algorithm is used to obtain the planned path for executing the corresponding assigned task;

[0052] S4. When the corresponding transport vehicle travels along the corresponding route, the energy storage status and vehicle operation status of the transport vehicle are monitored in real time, and the vehicle energy consumption model is used to monitor and warn the vehicle energy status. When the energy is lower than the energy status required for task execution, the transport vehicle is warned;

[0053] S5. According to the energy reserve status, vehicle operation status and supply station distribution status of the transport vehicle at the time of early warning, a recommendation algorithm is used to recommend a supply station to the corresponding transport vehicle, and according to the recommended supply station location information, a PID control algorithm path adjustment instruction is used to adjust the transport path in real time.

[0054] A computer-readable storage medium stores computer instructions, which, when executed, execute a vehicle transportation management method based on digital technology.

[0055] An electronic device comprises a memory and a processor. The memory stores a computer program. When the processor executes the computer program, a vehicle transportation management method based on digital technology is implemented.

[0056] Compared with the prior art, the present invention has the following beneficial effects:

[0057] 1. Aiming at the deficiencies of the prior art, the present invention comprehensively considers the task attributes, energy reserve status, transport vehicle evaluation scores and waiting time, and uses an intelligent allocation algorithm (such as a simulated annealing algorithm) to allocate tasks, thereby effectively avoiding scheduling conflicts and uneven resource allocation, while reducing the waiting time of vehicles and improving overall transportation efficiency;

[0058] 2. In view of the deficiencies of the prior art, the present invention combines factors such as vehicle energy consumption model, real-time energy reserve status, vehicle load, road conditions, driving efficiency score, etc. to dynamically plan the transportation route and predict the route length and the number of required replenishments. It realizes intelligent route planning based on remaining power, expected energy consumption and the availability of charging facilities along the way, effectively reducing the risk of inefficient intermediate stops or power exhaustion. At the same time, the energy consumption early warning mechanism can monitor the energy status in real time and issue early warning, further ensuring the smooth progress of the transportation task. BRIEF DESCRIPTION OF THE DRAWINGS

[0059] Figure 1 This is a module structure diagram of a vehicle transportation management system based on digital technology in Example 1 of the present invention;

[0060] Figure 2 This is a workflow diagram of a vehicle transportation management system based on digital technology according to Embodiment 2 of the present invention;

[0061] Figure 3 This is a flow chart of a vehicle transportation management method based on digital technology according to Embodiment 3 of the present invention. DETAILED DESCRIPTION

[0062] Example 1

[0063] See also Figure 1 , an embodiment provided by the present invention: a vehicle transportation management system based on digital technology, comprising: a vehicle monitoring module, an intelligent scheduling module, a cargo management module and a report generation module;

[0064] The vehicle monitoring module is used to monitor the energy storage and usage status of the vehicle in real time, and dynamically adjust the task execution process according to the energy storage and usage status;

[0065] The vehicle monitoring module includes a vehicle monitoring unit, a consumption prediction and warning unit, and a supply recommendation unit;

[0066] The vehicle monitoring unit is used to monitor and obtain the energy reserve status, vehicle operation status and vehicle detection data of the transport vehicle in the process of transport or non-transportation in real time, and visualize the obtained energy reserve status; further, in this embodiment, the energy reserve status includes: fuel / power level, energy consumption rate and energy efficiency; the vehicle operation status includes vehicle load, road condition, driving efficiency score, vehicle position, speed and acceleration, engine status and brake system status;

[0067] The consumption prediction and warning unit is used to construct a vehicle energy consumption model, and combine the energy reserve status of the transport vehicle, the vehicle load, the road condition, the driving efficiency score and the path length of the corresponding task to predict the path length of the vehicle within the normal driving time under the current energy reserve status and the number of times the corresponding task planning path needs to be replenished. At the same time, according to the predicted path length within the normal driving time and the actual path length of the transport vehicle corresponding to the task, an energy shortage warning is issued; further, in this embodiment, the normal driving time refers to the length of time the transport vehicle spends on the path before receiving the energy shortage warning;

[0068] A supply recommendation unit is used to recommend supply stations to corresponding transport vehicles through a recommendation algorithm based on the real-time acquired vehicle energy reserve status and supply station distribution status, so that the time to reach the supply station and the energy consumption are minimized; further, the recommendation algorithm in this embodiment includes an association rule and a recommendation algorithm based on Chinese pre-trained Bert;

[0069] Intelligent scheduling module, used to automatically optimize the scheduling and route planning of transport vehicles and reduce the idle rate of transport vehicles during task execution; the intelligent scheduling module includes a task allocation unit, a route planning unit and a route adjustment unit;

[0070] The task allocation unit is used to allocate corresponding tasks to each transport vehicle through an intelligent allocation algorithm according to the attributes of the assigned tasks, energy reserve status, transport vehicle status evaluation score and transport vehicle waiting time, so that the corresponding task execution time is the shortest and the transport vehicle with the longest waiting time is assigned the highest probability of the task, while reducing the vehicle idle driving rate;

[0071] A path planning unit is used to dynamically plan the path of the transport vehicle assigned the task through a path planning algorithm according to the assigned task attributes, energy reserve status, vehicle operation status and distribution of supply stations; further, the path planning algorithm in this embodiment includes a Dijkstra algorithm, an A* algorithm or an ant colony optimization algorithm (ACO);

[0072] A path adjustment unit is used to generate a path adjustment instruction according to the location information of the supply station recommended by the supply recommendation unit and the PID control algorithm, and input the generated path adjustment instruction to the path planning unit to adjust the transportation path of the corresponding transportation vehicle in real time;

[0073] The cargo management module is used to determine the transportation status of the cargo based on the real-time monitored cargo weight and vehicle running trajectory, to avoid illegal dumping and theft of cargo during transportation; the cargo management module includes a path abnormality monitoring unit and a cargo abnormality monitoring unit;

[0074] The path abnormality monitoring unit is used to monitor the driving trajectory of the transport vehicle in real time, and use the abnormality discrimination algorithm to monitor and determine whether the vehicle transportation trajectory is abnormal in real time; further, the specific steps of the path abnormality monitoring unit in this embodiment include:

[0075] D1. Acquire the real-time location data, driving status data and historical driving data of the transport vehicle, and pre-process the acquired data; in this embodiment, the real-time location data of the vehicle includes the location coordinates of the vehicle continuously collected through GPS or other positioning technologies; the driving status data includes the speed, direction and acceleration data of the transport vehicle; the historical driving data includes the historical driving route and behavior pattern of the vehicle;

[0076] D2. According to the pre-processed data, an abnormality discrimination model of the normal driving trajectory of the vehicle is constructed through an association rule algorithm, and the acquired data is used to train the abnormality discrimination model to obtain a trained abnormality discrimination model; further, in this embodiment, the abnormality discrimination model is judged in parallel through three directions: spatial deviation, time deviation and behavioral abnormality, wherein the spatial deviation refers to when the energy state of the transport vehicle is sufficient, Z consecutive position points deviate from the transport path planned and adjusted by the path planning unit, and it is judged as abnormal; the time deviation refers to the driving time of the transport vehicle on a certain section of the road is greater than 1.5 times the average time spent by the transport vehicle on normal driving on the section, which is judged as abnormal; the behavioral abnormality refers to the deceleration and acceleration frequency of the transport vehicle per unit time exceeding twice the deceleration and acceleration frequency per unit time of normal driving, which is judged as abnormal;

[0077] D3. The acquired abnormality discrimination model is built into the path abnormality monitoring unit, and the path abnormality monitoring unit is used to discriminate the abnormality of the driving trajectory of the transport vehicle according to the real-time acquired transport vehicle position data and driving status data;

[0078] The cargo abnormality monitoring unit is used to monitor the type and weight of the transported cargo in real time, and determine whether the transportation status of the transported cargo is abnormal through a matching algorithm; further, in this embodiment, the cargo abnormality monitoring unit monitors the cargo transported by the transport vehicle corresponding to the task in real time through a visual sensor and a gravity sensor. When the vehicle fails to reach the target point specified in the task, the cargo type and weight obtained by the visual sensor and the gravity sensor do not match the cargo type and weight recorded in the corresponding task attributes, the transported cargo is determined to be abnormal.

[0079] The report generation module is used to automatically monitor vehicle abnormalities and generate vehicle status reports based on the status data of the vehicle as a whole and its components acquired through real-time or periodic monitoring, and to provide feedback on the generated vehicle status reports to improve management efficiency;

[0080] The report generation module includes a vehicle status detection unit and a report generation feedback unit;

[0081] The vehicle state detection unit is used to perform real-time or periodic state score evaluation on the transport vehicle according to the acquired vehicle detection data through a comprehensive fuzzy evaluation algorithm, obtain the state evaluation score, and determine the vehicle operation ability according to the state evaluation score, and feed back the determination result to the task allocation unit; further, the data of the vehicle periodic detection includes: engine performance data, transmission system data, brake system data, suspension system data, tire data and driving assistance system data; the engine performance data includes engine speed, coolant temperature, fuel pressure, exhaust temperature and ignition system status; the transmission system data includes transmission oil temperature, transmission gear and clutch wear status; the brake system data includes brake fluid level, brake pad thickness, brake disc wear and ABS system status; the suspension system data includes shock absorber working status and spring status; the tire data includes tire pressure and tire wear degree; the driving assistance system data includes navigation system status, reversing radar / camera function and adaptive cruise control system status;

[0082] The report generation feedback unit is used to regularly generate corresponding transport vehicle inspection reports through a text generation algorithm based on the acquired vehicle periodic inspection data, vehicle operating status, and transport vehicle status evaluation scores, and to provide feedback on the generated reports through the system interactive interface to assist in the regular maintenance and overhaul of the corresponding transport vehicles. Furthermore, the text generation algorithms in this embodiment include: GPT (Generative Pre-trained Transformer) series, MASS, XLNet, and XLM models;

[0083] Furthermore, the specific steps of the consumption prediction and warning unit predicting the path length of the vehicle within the normal driving time under the current energy reserve state through the vehicle energy consumption model include:

[0084] A1. Obtain historical energy reserve status, vehicle load, road condition, driving efficiency score and energy consumption data per unit length of N types of transport vehicles, and pre-process the acquired data;

[0085] A2: Use support vector machine to build a vehicle energy consumption model, and use the preprocessed data in A1 to build the vehicle energy consumption model input sequence ,in, It indicates the energy reserve status of the nth type of transport vehicle monitored at the current time t. It indicates that the load status data of the nth type of transport vehicle is monitored at the current time t. Indicates the road status data of the transport vehicle monitored at the current time t. It indicates the driving efficiency score corresponding to the nth type of transport vehicle monitored at the current time t. It indicates the amount of energy consumed by the transport vehicle to reach the nearest supply station at the current time t. represents the reserved energy threshold; it is a fixed constant, which is set by those skilled in the art based on historical experience or experiments;

[0086] Furthermore, the specific steps for obtaining the driving efficiency score in A2 include:

[0087] A21. Collect and obtain the driving status data of the nth type of transport vehicle per unit length in real time through the on-board sensors of the transport vehicle, including acceleration, braking action, driving speed, idling time and the total number of vehicles per unit area;

[0088] A22. Construct driving efficiency evaluation indicators based on the acquired data, including acceleration smoothness, braking frequency, average speed, average idling time and road congestion;

[0089] A23. Based on the acquired driving efficiency evaluation index, a scoring formula for the corresponding evaluation index is constructed. Based on the acquired scoring formula for the evaluation index and the real-time acquired driving status data per unit length of the transport vehicle, the corresponding evaluation index score is calculated, which is specifically:

[0090]

[0091] in, represents the acceleration smoothness score of the nth type of transport vehicle, K represents the average number of accelerations of the nth type of transport vehicle per unit length, represents the acceleration value of the transport vehicle at the kth acceleration, represents the braking frequency score of the nth type of transport vehicle, M represents the average number of braking times of the nth type of transport vehicle per unit length, It indicates the intensity of the mth braking of the transport vehicle, that is, the acceleration value during deceleration; represents the average speed score of the nth type of transport vehicle, It represents the average speed of the nth type of transport vehicle per unit length. and represents the maximum and minimum energy-saving speed interval thresholds of the nth type of transport vehicle, and The specific settings are made by those skilled in the art based on experience or experiments; represents the average idling time score of the nth type of transport vehicle, It represents the average idling time of the nth type of transport vehicle within a unit length. It represents the total driving time of the nth type of transport vehicle within a unit length; represents the congestion degree of the transport vehicle during its travel at time t, represents the total number of vehicles in the unit area S corresponding to the transport vehicle at time t. Furthermore, in this embodiment, the corresponding unit area S is the area within 100 meters before and after the transport vehicle in the driving path of the transport vehicle;

[0092] A24. Based on the index scores obtained in A23, the driving efficiency score of the nth type of transport vehicle is calculated using a weighted strategy. , the weighted strategy is as follows: ,in, and Indicates the weighting coefficient of the corresponding indicator score;

[0093] A3. Input the obtained input sequence X into the vehicle energy consumption model for training, and fit the corresponding path length formula within the normal driving time, which is: ,in It represents the path length of the nth type of transport vehicle within the normal driving time at the current moment. The function representing the energy consumption per unit distance of the nth type of transport vehicle;

[0094] A4. The trained vehicle energy consumption model is built into the consumption prediction and early warning unit. According to the real-time monitored transport vehicle energy reserve status and vehicle operation status data, the corresponding transport vehicle’s energy consumption is calculated in real time. ; Further, in order to facilitate calculation in actual implementation, in this embodiment, the path length of the normal driving time corresponding to the current moment of the n-th type of transport vehicle is used as the path length of the normal driving time of a single transport vehicle of the corresponding type;

[0095] A5. According to the obtained The path planning unit assigns the total length of the task-planned path to the corresponding transport vehicle, and calculates the number of corresponding replenishments for the transport vehicle.

[0096] Furthermore, the specific steps of the consumption forecasting and warning unit for performing energy shortage warning include:

[0097] A6. Assume that the overall path length of the transport vehicle A corresponding to the task to be performed , the A4 real-time calculation results are and For comparison, if No warning will be given when When , assuming The corresponding path includes P supply stations, and the supply stations are divided according to their distance from the starting point of the task. Divided into P+1 driving intervals;

[0098] A7. The vehicle monitoring unit monitors the energy reserve status of the transport vehicle in P+1 driving intervals in real time. When the transport vehicle reaches the pth driving interval, the energy reserve status corresponding to the pth driving interval is - + When the transport vehicle A is warned of energy shortage, the energy reserve state and vehicle operation state of the transport vehicle at the time of the warning are input into the supply recommendation unit, and the best supply station is recommended for the transport vehicle with the warning; further, the specific steps of recommending the best supply station in this embodiment include:

[0099] A71. Obtain the vehicle energy reserve status, operating status data and distribution status data of all refueling stations at the time of early warning. The distribution status data of refueling stations includes location, charging / refueling capacity, current utilization rate and opening hours;

[0100] A72, construct a scoring recommendation model based on the random forest algorithm, and construct an objective function based on the acquired data, input the data acquired in A71 and the constructed objective function into the scoring recommendation model for training, and obtain the comprehensive score of each supply station; further, the objective function is specifically: ,in, It represents the total time from the current location to the i-th supply station, including the travel time plus the waiting time; It represents the shortest path length of the transport vehicle to the i-th supply station; represents the minimum energy reserve required to reach the i-th supply station, represents the average speed of the transport vehicle traveling to the i-th supply station, represents the waiting time of the transport vehicle at the i-th supply station; C represents the energy consumed per unit distance of the transport vehicle that performs the corresponding task, and Represents the objective function The weighting coefficient of

[0101] A73. Sort the supply stations according to the comprehensive scores, and select the supply station with the highest score to recommend to the corresponding transport vehicle;

[0102] A8. When the transport vehicle reaches the pth driving interval, the corresponding energy storage state is - > + When , no warning is issued for the transport vehicle traveling in the pth driving interval;

[0103] A9. Repeat steps A7 and A8 to make corresponding warning judgments for the remaining driving range, and issue energy shortage warnings based on the warning judgment results.

[0104] Furthermore, the specific steps performed by the task allocation unit include:

[0105] B1. Assume that there are U pending tasks and V transport vehicles at the current time. Set the uth pending task to be assigned to the task at the time. To the latest time point specified in the task attributes for task completion The window length is used as the priority of the corresponding task to be executed , specifically , set the vth transport vehicle to correspond to the length of the waiting time window As the priority of corresponding transport vehicles , specifically ;

[0106] B2, build a task allocation model through simulated annealing algorithm, using the obtained task and vehicle priorities, and the corresponding transport vehicle calculated by A4 The objective function of the task allocation model is constructed based on the number of replenishment , the objective function is , ;

[0107] in, represents the matching degree between the u-th task and the v-th transport vehicle, represents the task completion time after the v-th transport vehicle is assigned to task u; represents the minimum sum of the time required for V transport vehicles to complete U pending tasks, It represents the total route length of transport vehicle A when it travels normally throughout the journey without the need for resupply. the time spent;

[0108] Furthermore, the specific steps of obtaining the matching degree between the u-th task and the v-th transport vehicle in B2 include:

[0109] B21, based on the obtained tasks and vehicle priorities, and A4 calculated the corresponding transport vehicles The number of replenishment and the status assessment score of the corresponding transport vehicle Construct an input sequence and use the support vector machine to build a task matching model. Input the acquired input sequence into the task matching model for training, and fit the task matching model formula. The specific formula is:

[0110]

[0111] Among them, max represents the maximum value, represents the matching degree between the u-th task and the v-th transport vehicle, represents the number of times transport vehicle v needs to be replenished to perform task u, represents the status evaluation score of the vth transport vehicle obtained by the vehicle status detection unit, Represents the weight coefficient of task priority and vehicle priority, Indicates the weight coefficient of the impact of the number of replenishment times on the matching degree, is a constant value, which is used to prevent the denominator from being zero. It is set by those skilled in the art according to actual accuracy and experimental requirements. This formula not only takes into account the impact of task and vehicle priority, but also takes into account the impact of vehicle endurance, that is, the impact of the path length and number of replenishment times within the normal driving time on the matching degree. When allocating tasks, not only the vehicle priority is considered, but also the impact of vehicle endurance and vehicle health on the task completion time is considered, ensuring better matching of transport vehicles with high endurance and high score status with emergency tasks, while avoiding vehicles with frequent replenishment from taking on too many tasks. In this embodiment and Through the historical task matching process data obtained through experiments;

[0112] B22. The trained task matching model is built into the task allocation unit, and the matching degree between the task u to be assigned and the transport vehicle v is calculated based on the task attribute data and the transport vehicle usage status data and the evaluation score acquired in real time. The calculated matching degree is fed back to the task allocation model to allocate the corresponding task.

[0113] B3. Train the constructed task allocation model using the objective function and the task attribute data, vehicle attribute data and vehicle operation status data obtained through monitoring, and obtain the trained task allocation model, so that the probability of the vehicle with the highest priority among the V transport vehicles being assigned to the task is maximized when the U tasks to be executed are completed in the shortest time;

[0114] B4. The trained task allocation model is built into the task allocation unit, and the corresponding tasks are allocated according to the task attribute data, vehicle attribute data and vehicle operation status data acquired in real time.

[0115] This process ensures that urgent and important tasks are given priority by setting the priorities of tasks and vehicles. Secondly, the simulated annealing algorithm is used to build a task allocation model, and the task allocation strategy is optimized by comprehensively considering factors such as the matching degree between tasks and vehicles and the task completion time. In particular, the introduction of the task matching model not only considers the priorities of tasks and vehicles, but also fully considers the vehicle's endurance and status evaluation score, thereby achieving the best match between tasks and vehicles.

[0116] Furthermore, the specific steps of the vehicle state detection unit in this embodiment include:

[0117] C1. Use the mechanical performance, safety performance, electronic system performance, maintenance and servicing status, and energy efficiency of transport vehicles in the acquired vehicle inspection data to construct a first-level assessment factor set for transport vehicles;

[0118] C2. Construct the corresponding secondary evaluation factor set and evaluation index set based on the obtained primary evaluation factor set of the transport vehicle, and input the obtained primary evaluation factor set, secondary evaluation factor set and evaluation index set into the comprehensive fuzzy algorithm to score the transport vehicle status and obtain the status evaluation score of the vth transport vehicle. ; Further, in this embodiment, the secondary evaluation factor set corresponding to the mechanical performance of the transport vehicle includes engine performance, brake system efficiency and tire status; the secondary evaluation factor set corresponding to the safety performance includes active safety systems and passive safety equipment; the secondary evaluation factor set corresponding to the electronic system performance includes the navigation subsystem and the communication subsystem; the secondary evaluation factor set corresponding to the maintenance and servicing status includes the maintenance records of the last three months, the oil status and the battery health; the secondary evaluation factor set corresponding to the energy efficiency includes the energy conversion rate, the cruising range of the electric vehicle, the charging efficiency and the power transmission efficiency; the evaluation index set includes excellent, good, general and poor, and the scoring intervals corresponding to the evaluation index set are: the excellent corresponding interval is 15-20 points; the good corresponding interval is 10-14 points, the general corresponding interval is 5-9 points, and the poor corresponding interval is 0-4 points;

[0119] C3. Set comprehensive scoring threshold and ,when When , no task is assigned to the vth transport vehicle. When the vth transport vehicle can only participate in satisfying The allocation of tasks to be executed according to the conditions, when When the vth transport vehicle can participate in the allocation of all tasks to be performed; represents the median of the priorities of all tasks to be executed; further, in this embodiment, =15, =10;

[0120] C4, the status evaluation score of the corresponding v-th transport vehicle The results obtained in C3 are fed back to the task allocation unit to adjust the task matching allocation process.

[0121] Example 2

[0122] See also Figure 2 Another embodiment provided by the present invention is: a workflow step of a corresponding unit of a vehicle transportation management system based on digital technology includes:

[0123] First, the vehicle monitoring unit is used to monitor and obtain energy reserve status data, vehicle operation status data and vehicle detection data of the transport vehicle in a transport or non-transport state in real time, and the energy reserve status and vehicle operation status obtained are input into the consumption prediction and early warning unit to predict the path length of the vehicle within the normal driving time under the current energy reserve state and the number of times the corresponding task planning path needs to be replenished. At the same time, the obtained vehicle detection data is input into the vehicle state detection unit to obtain the state evaluation score of the corresponding transport vehicle, and the corresponding results obtained by the consumption prediction and early warning unit and the vehicle state detection unit are input into the task allocation unit to allocate tasks to each transport vehicle;

[0124] Second, according to the task data assigned to the transport vehicle, the energy reserve status of the transport vehicle and the distribution of the supply stations, the path planning unit is used to plan the path of the transport vehicle after the task is assigned, and the planned path is transmitted to the corresponding transport vehicle. After the corresponding transport vehicle performs the task according to the planned path, the vehicle monitoring unit monitors the energy reserve status and vehicle operation status of the transport vehicle in real time during operation, and the consumption prediction and early warning unit is used to monitor and warn the vehicle energy status. When the energy is lower than the energy status required for task execution, the transport vehicle is warned, and the energy reserve status of the transport vehicle at the time of the warning is input into the supply recommendation unit. According to the distribution status of the supply stations and the recommendation algorithm, the supply stations are recommended to the corresponding transport vehicles, and the location information of the supply stations obtained is input into the path adjustment unit to generate path adjustment instructions, and the generated path adjustment instructions are input into the path planning unit to adjust the transport path in real time, so that the adjusted path has the shortest time to reach the supply station and the transport target point;

[0125] Third, when the transport vehicle performs the task according to the planned route, the path abnormality monitoring unit and the cargo abnormality monitoring unit are started at the same time to monitor the abnormal situation of the transport vehicle's running trajectory and the quality and type of the transported cargo in real time during the transportation task, and upload and save the acquired abnormal situation to ensure the normal execution of the task and avoid illegal dumping and theft of goods during the transportation process.

[0126] Fourth, based on the status assessment score and vehicle detection data obtained by the vehicle status detection unit and the operating status data of each transport vehicle obtained by the vehicle monitoring unit, the corresponding transport vehicle detection report is regularly generated through the report generation feedback unit, and the generated report is fed back through the system interactive interface to assist in regular maintenance and overhaul of the vehicle.

[0127] Through real-time monitoring and predictive analysis, this process can accurately grasp the energy reserve status and operating status of the vehicle, so as to reasonably allocate tasks, optimize route planning, improve transportation efficiency, and reduce empty driving rate; secondly, during the transportation process, the route can be adjusted in real time to adapt to emergencies, such as energy shortages, to ensure efficient execution of tasks while reducing operating costs; thirdly, through the abnormal monitoring unit, violations and abnormal conditions of goods during transportation can be monitored in real time to ensure the compliance of transportation and the safety of goods; finally, the regularly generated vehicle inspection reports provide strong support for vehicle maintenance and overhaul, help extend the service life of the vehicle, and further improve the safety and economy of transportation.

[0128] Example 3

[0129] See also Figure 3 Another embodiment provided by the present invention is a vehicle transportation management method based on digital technology, comprising the following steps:

[0130] S1. Obtaining the energy storage status, vehicle operation status and vehicle detection data of the transport vehicle, and preprocessing the acquired data;

[0131] S2. Based on the pre-processed energy reserve state and vehicle operation state, the vehicle energy consumption model is used to predict the path length of the transport vehicle within the normal driving time under the current energy reserve and the number of replenishment times required for the corresponding task planning path. At the same time, the vehicle detection data is input into the vehicle state detection unit to obtain the state evaluation score of the corresponding transport vehicle;

[0132] S3. According to the output results of the vehicle energy consumption model, the vehicle status evaluation score and the task attribute data, the task matching model is used to assign the corresponding task to be performed to each transport vehicle, and according to the assigned task attributes and the operating status data of the corresponding transport vehicle, the path planning algorithm is used to obtain the planned path for executing the corresponding assigned task;

[0133] S4. When the corresponding transport vehicle travels along the corresponding route, the energy storage status and vehicle operation status of the transport vehicle are monitored in real time, and the vehicle energy consumption model is used to monitor and warn the vehicle energy status. When the energy is lower than the energy status required for task execution, the transport vehicle is warned;

[0134] S5. According to the energy reserve status, vehicle operation status and supply station distribution status of the transport vehicle at the time of early warning, a supply station is recommended to the corresponding transport vehicle through a recommendation algorithm, and according to the recommended supply station location information, a PID control algorithm path adjustment instruction is used to adjust the path in real time;

[0135] S6. When the transport vehicle performs the task according to the planned path, the path abnormality monitoring unit and the cargo abnormality monitoring unit are started to monitor the abnormal conditions of the running trajectory and the quality and type of the transported cargo of the transport vehicle in real time during the transportation task, and upload and save the acquired abnormal conditions to ensure the normal execution of the task.

[0136] Example 4

[0137] A computer-readable storage medium stores computer instructions, which, when executed, execute a vehicle transportation management method based on digital technology.

[0138] An electronic device comprises a memory and a processor. The memory stores a computer program. When the processor executes the computer program, a vehicle transportation management method based on digital technology is implemented.

[0139] The embodiments of the present invention are described above in conjunction with the accompanying drawings, but the present invention is not limited to the above-mentioned specific implementation modes, which are merely illustrative rather than restrictive. Under the guidance of the present invention, ordinary technicians in the field may also change, modify, replace and modify the above-mentioned embodiments without departing from the scope of protection of the purpose of the present invention and the claims, and all of these are within the protection of the present invention.

[0140] If the disclosed technical solution involves personal information, the product using the disclosed technical solution has clearly informed the personal information processing rules and obtained the individual's voluntary consent before processing the personal information. If the disclosed technical solution involves sensitive personal information, the product using the disclosed technical solution has obtained the individual's separate consent before processing the sensitive personal information, and at the same time meets the "explicit consent" requirement. For example, on personal information collection devices such as cameras, clear and prominent signs are set to inform that the personal information collection scope has been entered and personal information will be collected. If the individual voluntarily enters the collection scope, it is deemed that he or she agrees to the collection of his or her personal information; or on the device that processes personal information, when the personal information processing rules are notified by obvious signs / information, the individual's authorization is obtained through pop-up information or by asking the individual to upload his or her personal information; among them, the personal information processing rules may include information such as the personal information processor, the purpose of personal information processing, the processing method, and the type of personal information processed.

Claims

1. A vehicle transportation management system based on digital technology, characterized in that: include: Intelligent dispatch module, vehicle monitoring module and report generation module; The vehicle monitoring module includes a vehicle monitoring unit and a consumption prediction and early warning unit; The vehicle monitoring unit is used to monitor and obtain the energy reserve status, vehicle operation status and vehicle detection data of the transport vehicle in the process of transport or non-transportation in real time; the consumption prediction and early warning unit is used to construct a vehicle energy consumption model, and combine the energy reserve status, vehicle operation status and the path length of the corresponding task to predict the path length of the vehicle within the normal driving time and the number of times the corresponding task planning path needs to be replenished under the current energy reserve status, and at the same time, according to the predicted path length within the normal driving time and the actual path length of the transport vehicle corresponding to the task, an energy shortage early warning is issued; The intelligent scheduling module includes a task allocation unit; the task allocation unit is used to allocate corresponding tasks to each transport vehicle through an intelligent allocation algorithm according to the attributes of the assigned tasks, the energy reserve status, the transport vehicle status evaluation score and the transport vehicle waiting time; The report generation module includes a vehicle status detection unit; the vehicle status detection unit is used to perform real-time or periodic status score evaluation on the transport vehicle according to the acquired vehicle detection data through a comprehensive fuzzy evaluation algorithm, obtain the status evaluation score, and determine the vehicle operating capability according to the status evaluation score, and feed the determination result back to the task allocation unit.

2. A vehicle transportation management system based on digital technology as claimed in claim 1, characterized in that: The vehicle operation status includes vehicle load, road condition and driving efficiency score; the intelligent scheduling module also includes a path planning unit; the consumption prediction and early warning unit predicts the path length of the vehicle in the normal driving time under the current energy reserve state through the vehicle energy consumption model, and the specific steps include: A1. Obtain historical energy reserve status, vehicle load, road condition, driving efficiency score and energy consumption data per unit length of N types of transport vehicles, and pre-process the acquired data; A2: Use support vector machine to build a vehicle energy consumption model, and use the preprocessed data in A1 to build the vehicle energy consumption model input sequence ,in, It indicates the energy reserve status of the nth type of transport vehicle monitored at the current time t. It indicates that the load status data of the nth type of transport vehicle is monitored at the current time t. Indicates the road status data of the transport vehicle monitored at the current time t. It indicates the driving efficiency score corresponding to the nth type of transport vehicle monitored at the current time t. It indicates the amount of energy consumed by the transport vehicle to reach the nearest supply station at the current time t. represents the reserved energy threshold; A3. Input the obtained input sequence X into the vehicle energy consumption model for training, and fit the corresponding path length formula within the normal driving time, which is: ,in It represents the path length of the nth type of transport vehicle within the normal driving time at the current moment. The function representing the energy consumption per unit distance of the nth type of transport vehicle; A4. The trained vehicle energy consumption model is built into the consumption prediction and early warning unit. According to the real-time monitored transport vehicle energy reserve status and vehicle operation status data, the corresponding transport vehicle’s energy consumption is calculated in real time. ; A5. According to the obtained The path planning unit assigns the total length of the task-planned path to the corresponding transport vehicle, and calculates the number of corresponding replenishments for the transport vehicle.

3. A vehicle transportation management system based on digital technology as claimed in claim 2, characterized in that: The specific steps of obtaining the driving efficiency score in A2 include: A21. Collect and obtain the driving status data of the nth type of transport vehicle per unit length in real time through the on-board sensors of the transport vehicle, including acceleration, braking action, driving speed, idling time and the total number of vehicles per unit area; A22. Construct driving efficiency evaluation indicators based on the acquired data, including acceleration smoothness, braking frequency, average speed, average idling time and road congestion; A23. Based on the acquired driving efficiency evaluation index, a scoring formula for the corresponding evaluation index is constructed. Based on the acquired scoring formula for the evaluation index and the real-time acquired driving status data per unit length of the transport vehicle, the corresponding evaluation index score is calculated, which is specifically: ; in, represents the acceleration smoothness score of the nth type of transport vehicle, K represents the average number of accelerations of the nth type of transport vehicle per unit length, represents the acceleration value of the transport vehicle at the kth acceleration, represents the braking frequency score of the nth type of transport vehicle, M represents the average number of braking times of the nth type of transport vehicle per unit length, Indicates the intensity of the mth braking of the transport vehicle; represents the average speed score of the nth type of transport vehicle, It represents the average speed of the nth type of transport vehicle per unit length. and represents the maximum and minimum energy-saving speed interval thresholds of the nth type of transport vehicle, represents the average idling time score of the nth type of transport vehicle, It represents the average idling time of the nth type of transport vehicle within a unit length. It represents the total driving time of the nth type of transport vehicle within a unit length; represents the congestion degree of the transport vehicle during its travel at time t, It represents the total number of vehicles in the unit area S corresponding to the transport vehicles at time t; A24. Based on the index scores obtained in A23, the driving efficiency score of the nth type of transport vehicle is calculated using a weighted strategy. , the weighted strategy is as follows: ,in, and Indicates the weighting coefficient of the corresponding indicator score.

4. A vehicle transportation management system based on digital technology as claimed in claim 3, characterized in that: The specific steps of the consumption prediction and warning unit for performing energy shortage warning include: A6. Assume that the overall path length of the transport vehicle A corresponding to the task to be performed , the A4 real-time calculation results are and For comparison, if No warning will be given when When , assuming The corresponding path includes P supply stations, and the supply stations are divided according to their distance from the starting point of the task. Divided into P+1 driving intervals; A7. The vehicle monitoring unit monitors the energy reserve status of the transport vehicle in P+1 driving intervals in real time. When the transport vehicle reaches the pth driving interval, the energy reserve status corresponding to the pth driving interval is - + When the energy shortage warning is issued to the transport vehicle A; A8. When the transport vehicle reaches the pth driving interval, the corresponding energy storage state is - > + When , no warning is issued for the transport vehicle traveling in the pth driving interval; A9. Repeat steps A7 and A8 to make corresponding warning judgments for the remaining driving range, and issue energy shortage warnings based on the warning judgment results.

5. A vehicle transportation management system based on digital technology as claimed in claim 4, characterized in that: The specific steps performed by the task allocation unit include: B1. Assume that there are U pending tasks and V transport vehicles at the current time. Set the uth pending task to be assigned to the task at the time. To the latest time point specified in the task attributes for task completion The window length is used as the priority of the corresponding task to be executed , specifically , set the vth transport vehicle to correspond to the length of the waiting time window As the priority of corresponding transport vehicles , specifically ; B2, build a task allocation model through simulated annealing algorithm, using the obtained task and vehicle priorities, and the corresponding transport vehicle calculated by A4 The objective function of the task allocation model is constructed based on the number of replenishment , the objective function is specifically: , ; in, represents the matching degree between the u-th task and the v-th transport vehicle, represents the task completion time after the v-th transport vehicle is assigned to task u; It represents the minimum sum of time required for V transport vehicles to complete U tasks to be performed; B3. Train the constructed task allocation model using the objective function and the task attribute data, vehicle attribute data and vehicle operation status data acquired through monitoring, and obtain the trained task allocation model; B4. The trained task allocation model is built into the task allocation unit, and the corresponding tasks are allocated according to the task attribute data, vehicle attribute data and vehicle operation status data acquired in real time.

6. A vehicle transportation management system based on digital technology as claimed in claim 5, characterized in that: The specific steps of obtaining the matching degree between the u-th task and the v-th transport vehicle in B2 include: B21, based on the obtained tasks and vehicle priorities, and A4 calculated the corresponding transport vehicles The number of replenishment and the status assessment score of the corresponding transport vehicle Construct an input sequence and use the support vector machine to build a task matching model. Input the acquired input sequence into the task matching model for training, and fit the task matching model formula. The specific formula is: ; Among them, max represents the maximum value, represents the matching degree between the u-th task and the v-th transport vehicle, represents the number of times transport vehicle v needs to be replenished to perform task u, represents the status evaluation score of the vth transport vehicle obtained by the vehicle status detection unit, Represents the weight coefficient of task priority and vehicle priority, Indicates the weight coefficient of the impact of the number of replenishment times on the matching degree, is a constant value; B22. The trained task matching model is built into the task allocation unit, and the matching degree between the task u to be assigned and the transport vehicle v is calculated based on the task attribute data and the transport vehicle usage status data and the evaluation score acquired in real time. The calculated matching degree is fed back to the task allocation model to allocate the corresponding task.

7. A vehicle transportation management system based on digital technology as claimed in claim 6, characterized in that: The specific steps of the vehicle state detection unit include: C1. Use the mechanical performance, safety performance, electronic system performance, maintenance and servicing status, and energy efficiency of transport vehicles in the acquired vehicle inspection data to construct a first-level assessment factor set for transport vehicles; C2. Construct the corresponding secondary evaluation factor set and evaluation index set based on the obtained primary evaluation factor set of the transport vehicle, and input the obtained primary evaluation factor set, secondary evaluation factor set and evaluation index set into the comprehensive fuzzy algorithm to score the transport vehicle status and obtain the status evaluation score of the vth transport vehicle. ; C3. Set comprehensive scoring threshold and ,when When , no task is assigned to the vth transport vehicle. When the vth transport vehicle can only participate in satisfying The allocation of tasks to be executed according to the conditions, when When the vth transport vehicle can participate in the allocation of all tasks to be performed; Represents the median priority of all tasks to be executed; C4, the status evaluation score of the corresponding v-th transport vehicle The results obtained in C3 are fed back to the task allocation unit to adjust the matching allocation process of the tasks.

8. A vehicle transportation management method based on digital technology, which is implemented based on a vehicle transportation management system based on digital technology as claimed in any one of claims 1 to 7, characterized in that: include: S1. Obtaining the energy storage status, vehicle operation status and vehicle detection data of the transport vehicle, and preprocessing the acquired data; S2. Based on the pre-processed energy reserve state and vehicle operation state, the vehicle energy consumption model is used to predict the path length of the transport vehicle within the normal driving time under the current energy reserve and the number of replenishment times required for the corresponding task planning path. At the same time, the vehicle detection data is input into the vehicle state detection unit to obtain the state evaluation score of the corresponding transport vehicle; S3. According to the output results of the vehicle energy consumption model, the vehicle status evaluation score and the task attribute data, the task matching model is used to assign the corresponding task to be performed to each transport vehicle, and according to the assigned task attributes and the operating status data of the corresponding transport vehicle, the path planning algorithm is used to obtain the planned path for executing the corresponding assigned task; S4. When the corresponding transport vehicle travels along the corresponding route, the energy storage status and vehicle operation status of the transport vehicle are monitored in real time, and the vehicle energy consumption model is used to monitor and warn the vehicle energy status. When the energy is lower than the energy status required for task execution, the transport vehicle is warned; S5. According to the energy reserve status, vehicle operation status and supply station distribution status of the transport vehicle at the time of early warning, a recommendation algorithm is used to recommend a supply station to the corresponding transport vehicle, and according to the recommended supply station location information, a PID control algorithm path adjustment instruction is used to adjust the transport path in real time.

9. A computer-readable storage medium, characterized in that: Computer instructions are stored thereon, and when the computer instructions are executed, a vehicle transportation management method based on digital technology as described in claim 8 is executed.

10. An electronic device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the vehicle transportation management method based on digital technology described in claim 8 is implemented.

Citation Information

Patent Citations

  • Charging scheduling method for unmanned vehicle group and cloud management server

    CN110533901A

  • Electric vehicle charging path planning method and device and storage medium

    CN111220168A

  • Energy supply control method and device for vehicle

    CN112217888A

  • Intelligent horizontal transportation system and method for full-automatic container loading and unloading wharf.

    CN113486293A

  • Transportation task allocation method and system

    CN118278667A

Cited By

  • Transport vehicle reservation management scheduling system and method based on Internet of Things

    CN120012964A

  • Internet of Things-based transportation vehicle reservation management and scheduling system and method

    CN120012964B

  • Intelligent dispatching management system of coal mine monorail crane locomotive

    CN120317597A

  • Remote health monitoring method and system for starting and flameout of excavator

    CN120972869A

  • AI-based cargo transportation real-time safety early warning and path optimization system

    CN120996684A