Vehicle transportation management method and system based on digital technology

Abstract

The invention relates to the technical field of logistics transportation management, and discloses a vehicle transportation management method based on a digital technology, and the method comprises the following steps: collecting the energy state data of a vehicle in real time through a vehicle monitoring module; transmitting the collected vehicle data to a big data platform by using an Internet of Things technology, analyzing the data, and generating an early warning signal of an energy state; when the early warning signal is triggered, determining an optimal supply path according to the current position of the vehicle and traffic information, and arranging an energy supply service in advance; and through an intelligent scheduling module, according to real-time traffic information, vehicle load and destination distance factors, a transportation route and task distribution of the vehicle are dynamically adjusted. Through real-time monitoring and analysis, the system can automatically trigger a supply early warning signal when the energy state is lower than a safety threshold value, so that non-planned parking caused by energy exhaustion is avoided, and the accuracy of energy management and the operation reliability are remarkably improved.

Description

Technical Field

[0001] The present invention relates to the technical field of logistics transportation management, and in particular to a vehicle transportation management method and system based on digital technology. Background Art

[0002] With the rapid development of the logistics and transportation industry, the application of vehicle transportation management systems in modern logistics has become more and more extensive. However, the widely used traditional transportation management systems still have many shortcomings at the technical level, which limit the efficiency improvement and operation optimization of the industry.

[0003] On the one hand, traditional transportation management systems mainly rely on fixed-rule route planning and task allocation models, and cannot dynamically respond to complex and changing transportation environments. For example, when transport vehicles encounter traffic congestion, bad weather or other emergencies, the system lacks the ability to effectively collect and analyze real-time traffic data, making it difficult to provide fast and flexible scheduling solutions, often resulting in low transportation efficiency, increased idle driving rate and energy consumption.

[0004] On the other hand, in terms of energy management, existing technologies usually use simple periodic inspections or manual monitoring methods, which are unable to collect and analyze the vehicle's energy status (such as battery power, fuel level, etc.) in real time. Therefore, when the vehicle's energy is about to run out, the failure to issue a timely warning or plan a replenishment plan in advance often leads to unplanned stops, affecting the timely completion of the transportation task.

[0005] In addition, in the process of cargo management, traditional systems usually rely solely on manual monitoring of cargo status, lacking real-time data collection and abnormal alarm mechanisms. This method is particularly insufficient for scenarios with high requirements for transportation conditions, such as cold chain logistics and dangerous goods transportation, and is prone to cause cargo quality loss or transportation safety hazards, further exacerbating the operational risks and cost burdens of logistics companies.

[0006] In terms of vehicle performance management, traditional transportation management systems lack in-depth mining and analysis of historical driving data. The health of vehicles is usually maintained through regular manual inspections or empirical judgments. This lagging and extensive management method not only increases maintenance costs, but may also lead to potential faults not being discovered in time, thus causing sudden vehicle failures, resulting in transportation interruptions and serious economic losses. Summary of the invention

[0007] In view of the shortcomings of the prior art, the present invention provides a vehicle transportation management method and system based on digital technology, which solves the problems of slow response speed, inflexible scheduling, extensive energy management, poor cargo safety and insufficient vehicle performance evaluation of the existing transportation management system.

[0008] To achieve the above objectives, the present invention is implemented through the following technical solutions: A vehicle transportation management method based on digital technology, comprising the following steps: Collect the vehicle's energy status data in real time through the vehicle monitoring module; Use IoT technology to transmit collected vehicle data to a big data platform, analyze the data, and generate early warning signals for energy status; When the warning signal is triggered, the optimal refueling route is determined based on the vehicle’s current location and traffic information, and energy refueling services are arranged in advance; Through the intelligent scheduling module, the transportation routes and task allocation of vehicles are dynamically adjusted according to real-time traffic information, vehicle load, and destination distance factors; The cargo management module monitors cargo status in real time and generates alarm signals in case of abnormal conditions; Generate vehicle performance evaluation reports based on historical driving data, predict potential failures, and push maintenance recommendations.

[0009] Preferably, the data collected by the vehicle monitoring module includes vehicle battery power, fuel level, engine temperature and geographic location information, and the data is transmitted to the big data platform at a predetermined frequency through the Internet of Things communication module.

[0010] Preferably, the big data platform analyzes the vehicle energy status data, generates a replenishment warning signal by comparing the current remaining energy with a preset safety threshold, and calculates the optimal path to the replenishment station in combination with the vehicle's geographic location and traffic data.

[0011] Preferably, the step of dynamically adjusting vehicle transportation routes and task allocation through the intelligent scheduling module includes: Calculate transportation time and empty driving rate based on real-time traffic information; Optimize routes to minimize transit time and empty trips, while taking into account vehicle load and distance to destination.

[0012] Preferably, the cargo management module collects cargo status data in real time through a sensor network and sets a safety threshold. If the monitoring data exceeds a safety range, an abnormal alarm signal is generated and pushed to the management system.

[0013] Preferably, the cargo management module monitors the transportation track of the cargo in real time and generates an alarm message when the track deviates from the preset path.

[0014] A vehicle transportation management system based on digital technology, comprising: Vehicle monitoring module, used to collect vehicle energy status data in real time; IoT communication module, used to transmit collected vehicle data to the big data platform; Big data analysis module, used to analyze the energy status of the vehicle and generate replenishment warning signals; Intelligent scheduling module, used to dynamically adjust transportation routes and task allocation according to real-time traffic information, vehicle status and transportation demand; cargo management module, used to monitor the status of cargo and generate alarm signals when abnormalities occur; Report generation module, used to generate vehicle performance evaluation reports based on historical data, predict failures and provide maintenance recommendations.

[0015] Preferably, the intelligent scheduling module optimizes the transportation task allocation through a machine learning algorithm, and the algorithm adjusts the scheduling strategy based on historical task allocation results and real-time transportation conditions.

[0016] Preferably, the report generation module uses a time series analysis algorithm to analyze historical vehicle driving data to predict potential failures of vehicle components and provide maintenance recommendations.

[0017] Preferably, the vehicle monitoring module collects energy status data of the vehicle through a high-precision sensor, and the data collection frequency of the sensor can be dynamically adjusted.

[0018] The present invention provides a vehicle transportation management method and system based on digital technology. It has the following beneficial effects: 1. The present invention collects the vehicle's energy status data (such as battery power, fuel level and engine temperature) in real time through the vehicle monitoring module, and combines the Internet of Things technology and big data analysis to accurately calculate the vehicle's remaining energy and driving time. Through real-time monitoring and analysis, the system can automatically trigger a replenishment warning signal when the energy status is below the safety threshold, thereby avoiding unplanned parking due to energy exhaustion, significantly improving the accuracy of energy management and operational reliability.

[0019] 2. The present invention uses an intelligent scheduling module to dynamically adjust the transportation routes and task allocation of vehicles by comprehensively considering multi-dimensional factors such as real-time traffic information, vehicle load and destination distance. Based on the path planning algorithm and reinforcement learning model, the system can effectively cope with complex and changeable traffic conditions, optimize transportation routes, and minimize empty driving rate and transportation costs, thereby improving the efficiency and flexibility of the entire transportation network.

[0020] 3. The present invention monitors the status information of the goods (including temperature, humidity, vibration, etc.) in real time through the goods management module, and generates an alarm signal immediately when the goods status is abnormal, notifying the driver and the management system to take emergency measures. This function is particularly suitable for cold chain logistics or goods with high requirements for transportation conditions, which can effectively prevent damage to goods, ensure the quality of goods, and reduce the risk of goods loss during transportation.

[0021] 4. The present invention uses a report generation module to scientifically evaluate vehicle performance based on historical driving data, calculate vehicle health index and predict potential failures. By introducing time series analysis and machine learning technology, the system can generate maintenance suggestions in advance and notify relevant personnel, thereby avoiding unexpected downtime caused by vehicle failures, improving the reliability and service life of vehicle operation, and reducing operating and maintenance costs. BRIEF DESCRIPTION OF THE DRAWINGS

[0022] Figure 1 is a flow chart of the method of the present invention; Figure 2 It is a system architecture diagram of the present invention. DETAILED DESCRIPTION

[0023] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. 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 creative work are within the scope of protection of the present invention.

[0024] Example: Please see attached Figure 1 -Attached Figure 2 The embodiment of the present invention provides a vehicle transportation management method based on digital technology, comprising the following steps: S1. Collect the energy status data of the vehicle in real time through the vehicle monitoring module; In the process of vehicle transportation management, in order to achieve efficient energy monitoring and management and ensure the controllability and accuracy of the vehicle's energy status during operation, the solution of the present invention proposes a technical method for real-time collection of key energy status data of the vehicle by integrating a vehicle monitoring module. It should be noted that this step, as the basic link of the entire vehicle transportation management method, directly affects the normal operation of the subsequent energy supply warning and transportation scheduling modules due to the accuracy and timeliness of the collected data. In the implementation of this step, high-precision sensors, data preprocessing algorithms and Internet of Things communication technologies are comprehensively used to ensure the reliability and real-time nature of energy data collection.

[0025] In this embodiment, the vehicle monitoring module includes a high-precision power sensor, a fuel sensor, and a temperature sensor, etc., which are used to collect the energy status data of the vehicle in real time. These data include but are not limited to the battery power (E b ), fuel quantity (F t ), engine temperature (T e ) and the vehicle’s current geographic location (GPS data).

[0026] As an option, the vehicle monitoring module is connected to the sensor through an embedded acquisition unit, which collects vehicle status data at a preset sampling frequency. For example, the sampling frequency can be set to 10 times per second, and the specific frequency can be dynamically adjusted according to the vehicle operation status to increase the acquisition frequency in critical operation scenarios (such as high-speed driving or low energy status).

[0027] It should be noted that the collected data often contains noise interference, so in some embodiments, a filtering algorithm is used to pre-process the raw data. Specifically, the present invention preferably uses a Kalman filtering algorithm, which eliminates instantaneous fluctuations in the data by dynamically estimating the current energy state, making the collected data more stable.

[0028] In one possible implementation, the state estimation formula of the Kalman filter is: in: Indicates the estimated value of energy status at the current moment; z k Represents the observation value collected by the sensor; K k is the Kalman gain, and the calculation formula is: P k-1 is the prior estimation error covariance matrix, H k is the observation matrix, and R is the covariance of the observation noise.

[0029] Specifically, the above-mentioned filtering algorithm optimizes the vehicle's energy status assessment in real time by continuously adjusting the weights of estimation error and observation error, thereby significantly improving the accuracy of subsequent energy replenishment warnings.

[0030] Exemplarily, the collected energy status data (such as battery power and fuel quantity) is uploaded to the big data platform through the Internet of Things communication module. As an implementation, the communication module can use 4G, 5G network or low-power wide area network (LoRa, NB-IoT) protocol for data transmission to ensure the real-time and low latency of the data. It should be noted that the choice of communication protocol can be adjusted according to the different operating environments of the vehicle. For example, 5G communication is preferred in highway environments to ensure high-speed transmission, while NB-IoT technology can be preferred in remote areas to achieve low-power long-distance communication.

[0031] In some embodiments, the vehicle monitoring module further integrates a fault detection unit for collecting abnormal parameters related to the vehicle energy status, such as unstable battery voltage or fuel leakage signals. These abnormal parameters can be collected through the vehicle self-diagnosis system (OBD) interface and marked as "need attention" when the data is uploaded to the cloud platform.

[0032] It is understandable that the data collection and transmission process needs to meet certain reliability requirements. In another possible implementation, the vehicle monitoring module also includes a data cache unit for temporarily storing the collected data when the communication network is unstable and automatically retransmitting it after the signal is restored. This design can avoid data loss caused by network interruption.

[0033] It should be noted that the design of the vehicle monitoring module in the present invention takes into account the optimization of both hardware and software levels. For example, at the hardware level, low-power and high-precision sensor components are selected to reduce system energy consumption; at the software level, a multi-threaded data acquisition mechanism is introduced to ensure that multiple types of data (such as battery power, fuel level, engine temperature, etc.) can be synchronously collected and processed separately.

[0034] In the extended implementation, the vehicle monitoring module can further integrate environmental parameter monitoring functions, such as collecting temperature and humidity data around the vehicle. Although these data are not directly used for energy status analysis, they can provide necessary environmental background information for the subsequent cargo monitoring module, thereby enhancing the intelligence and coordination capabilities of the entire system.

[0035] In summary, this step realizes the efficient and real-time collection of vehicle energy status data through the vehicle monitoring module, providing a reliable data basis for subsequent energy supply warning and intelligent scheduling.

[0036] S2. Use IoT technology to transmit the collected vehicle data to the big data platform, analyze the data, and generate early warning signals for energy status; The scheme of the present invention realizes the real-time transmission of data collected by the vehicle monitoring module and the intelligent analysis of the energy status through the combination of Internet of Things communication technology and big data analysis technology. It should be noted that this step plays a key role in connecting the previous and the next steps in the system. It not only realizes the transmission of data, but also generates an early warning signal of the energy status by analyzing the transmitted data, providing support for subsequent energy replenishment and intelligent scheduling. This scheme focuses on the timeliness and accuracy of data transmission and the intelligence of energy status analysis to ensure the efficient operation of the vehicle transportation management system.

[0037] In this embodiment, the collected vehicle data is uploaded to the big data platform through the IoT communication module. The communication module supports a variety of wireless communication protocols, including but not limited to 4G, 5G, LoRa and NB-IoT, to meet the data transmission requirements in different scenarios. For example, 5G networks can be preferred in urban areas to achieve high-bandwidth and low-latency real-time transmission, while NB-IoT technology can be preferred in remote areas to reduce power consumption and extend communication distance.

[0038] As an option, data transmission adopts a layered architecture design, including data collection layer, transmission layer and storage layer. Specifically, the collection layer is composed of data packets generated by the vehicle monitoring module, the transmission layer is responsible for real-time data upload through the communication module, and the storage layer stores data in the form of a distributed database in the big data platform. For example, HDFS (Hadoop Distributed File System) or NoSQL database is used for data management to ensure efficient storage and retrieval of large-scale data.

[0039] It should be noted that, in order to ensure the reliability of data transmission, the TCP / IP protocol is used for transmission control in this embodiment, and the possibility of data loss is reduced through the packet retransmission mechanism. At the same time, in another possible implementation, the data transmission can adopt the lightweight UDP protocol to improve the transmission efficiency, but at the same time combine the redundancy check mechanism to make up for the lack of UDP in terms of reliability.

[0040] In the data analysis part, the big data platform processes the transmitted vehicle data in real time, mainly including the calculation of energy status and the judgment of energy supply demand. Specifically, the system calculates the total remaining energy of the vehicle (E r ) and combined with the energy consumption rate (C t ), estimate the remaining driving time of the vehicle (T r ). The formula is as follows: E r =E b +F t Among them, E b is the battery capacity, F t is the fuel quantity, C t is the current energy consumption rate of the vehicle.

[0041] As a means of implementation, the energy consumption rate (C t ) can be adjusted dynamically based on the vehicle's real-time operating status, including the combined effects of vehicle speed, load, and road conditions. For example, on an uphill section, the system will adjust C t The calculation model is adapted to the higher energy consumption.

[0042] It should be noted that in order to improve the prediction accuracy of energy status, the system further uses machine learning models to model energy consumption trends. For example, a time series analysis model based on historical data (such as the ARIMA model) is used to dynamically predict the vehicle energy consumption rate. The prediction formula of the ARIMA model is as follows: y t =c+φ 1 y t-1 +φ 2 y t-2 +…+φ p y t-p +∈ t Among them, y t is the current energy consumption rate, φ i is the model parameter, ∈ t is the noise term.

[0043] In a possible implementation, the big data platform sets an early warning threshold (T th ), for example, when the remaining travel time T r When the time is less than 30 minutes, the warning signal is triggered. The generation of the warning signal includes marking the vehicle ID, remaining energy status and recommended supply stations, and pushing the signal to the dispatch terminal.

[0044] For example, in an urban logistics scenario, a vehicle currently has 50% remaining battery power, 20L fuel, and a consumption rate of 2L per minute and 10% power. The remaining driving time is calculated to be 25 minutes using the above formula. The system triggers a refueling signal based on the warning threshold and recommends the nearest refueling station based on the vehicle's geographic location and traffic information.

[0045] As an option, the accuracy of the energy status warning signal can be corrected by combining multi-dimensional parameters (such as historical failure rate, driving conditions and ambient temperature) during data analysis. For example, when an abnormally high engine temperature (T e >T th ), the system weights and adjusts the energy consumption rate to avoid underestimating energy demand.

[0046] It should be understood that in actual applications, the process of vehicle data transmission and analysis may be affected by network interruption or data anomaly. Therefore, in another implementation, the system also includes data buffering and retransmission functions. For example, when the signal is interrupted, the vehicle temporarily stores the data in the local cache, and retransmits it through the incremental upload mechanism after the communication is restored to ensure the integrity of the data.

[0047] In summary, this step realizes the efficient transmission of vehicle data through the Internet of Things technology, and conducts real-time analysis of data and intelligent early warning of energy status through the big data platform, providing a reliable decision-making basis for subsequent scheduling and supply modules.

[0048] S3. When the warning signal is triggered, determine the optimal replenishment route based on the vehicle’s current location and traffic information, and arrange energy replenishment services in advance; The core of the solution of the present invention is to respond to the triggered warning signal, use real-time vehicle location information and traffic status data, calculate and select an optimal supply route, and complete the arrangement of supply services in advance. It should be noted that this step not only ensures that the vehicle completes the supply in time before the energy is exhausted, but also minimizes the vehicle's driving time and empty driving rate, which is of great significance to improving the overall transportation efficiency. To achieve the above goals, the present invention adopts a dynamic path planning algorithm and multi-dimensional data analysis technology, and the specific technical implementation is as follows.

[0049] In this embodiment, after the remaining energy state of the vehicle is lower than the set threshold and triggers the warning signal, the system first obtains the current geographic location data (GPS coordinates) of the vehicle, and combines real-time traffic information (such as road congestion index and travel time) to construct a candidate set of feasible paths.

[0050] Specifically, traffic information is obtained based on the Internet of Things technology, and the data sources include real-time traffic data from the traffic monitoring center, traffic flow analysis results from third-party map services (such as Amap or Google Maps API), etc. Through dynamic evaluation of candidate paths, the system takes the optimal path as the objective function, calculates the driving cost and selects the optimal path.

[0051] As an option, the objective function of the optimal path can be based on vehicle travel time and empty rate, expressed as: min P (T route +α·R empty ) in: P is a path in the candidate path set; T route represents the travel time of the vehicle on path P; R empty It represents the empty driving rate, that is, the ratio of the empty distance of the vehicle on path P to the total driving distance; α is the weight coefficient of the empty driving rate, which can be adjusted dynamically according to actual operational needs.

[0052] In one possible implementation, path planning uses the A algorithm for dynamic calculation. The A algorithm achieves fast solution through heuristic estimation of path cost, and its estimation function is: f(n)=g(n)+h(n) in: f(n) represents the estimated total cost from the starting point to the target point; g(n) represents the actual travel cost from the starting point to node n; h(n) is a heuristic estimate of the distance from node n to the target point, for example using the Euclidean distance or the Manhattan distance.

[0053] It should be noted that in order to further improve the intelligence of path planning, some embodiments also combine traffic prediction models based on machine learning. Specifically, by analyzing historical traffic data and real-time traffic data, the system can predict traffic flow changes in the future, thereby dynamically adjusting the path cost.

[0054] After the route planning is completed, the system will push the recommended supply route information to the vehicle's on-board terminal. At the same time, based on the vehicle's remaining energy status and the service capabilities of the candidate supply stations, it will determine the target supply station and complete the reservation for the supply service.

[0055] For example, in an urban logistics and transportation scenario, when the remaining power of an electric vehicle triggers a warning signal, the system combines the vehicle's current location (such as a commercial district) and the target location (such as a distribution center) to select a route that passes through the nearest charging station and avoids peak congestion areas, and notifies the charging station in advance to reserve charging piles.

[0056] As a possible implementation method, the selection of refueling stations is based on a multi-factor optimization strategy. Specifically, the system conducts a comprehensive evaluation of refueling stations based on the following parameters: Distance: the shortest path distance from the vehicle’s current location to the supply station; Service capacity: the current available resources of the refueling station, such as the number of charging stations or refueling machines; Waiting time: estimated waiting time at the supply station; Operating costs: The fuel or electricity consumed by the vehicle to reach the supply station.

[0057] In order to achieve comprehensive processing of the above parameters, the solution of the present invention adopts a decision model based on weighted scoring, and its calculation formula is: S=w 1 ·D+w 2 ·A+w 3 ·W+w 4 ·C in: S is the comprehensive score, the smaller the value, the higher the preference of the refueling station; D is the distance weight factor; A is the service capability weight factor; W is the waiting time weight factor; C is the operating cost weight factor; w 1 ,w 2 ,w 3 ,w 4 is the corresponding weight parameter, which is adjusted according to actual operational needs.

[0058] In another possible implementation, in order to avoid supply failures caused by route planning errors or unavailable supply services, the system can also design alternative supply stations. When the service capacity of the target supply station drops to an unacceptable level, the system will automatically switch to the alternative supply station and re-plan the route.

[0059] It should be understood that in order to ensure the timeliness of the replenishment service, after completing the route planning and replenishment appointment, the system will also track the vehicle's driving status in real time, and issue an alarm when the vehicle deviates from the planned route to prompt the driver to return to the planned route.

[0060] In summary, the present invention not only ensures the timely replenishment of vehicle energy through dynamic path planning and intelligent supply station selection, but also minimizes the idle driving cost and time cost during the transportation process.

[0061] S4, through the intelligent scheduling module, dynamically adjust the vehicle's transportation route and task allocation according to real-time traffic information, vehicle load, and destination distance factors; The solution of the present invention uses an intelligent scheduling module to optimize the transportation routes and task allocation of vehicles, and dynamically adjusts transportation decisions by integrating multi-dimensional data such as real-time traffic information, vehicle load conditions, and distance to the destination. It should be noted that the implementation of this step is intended to improve transportation efficiency, reduce empty driving rates, and optimize resource allocation in the transportation network, especially in complex and changeable traffic environments. The present invention uses a combination of path planning algorithms and intelligent scheduling algorithms to ensure the intelligence and feasibility of transportation solutions.

[0062] In this embodiment, the intelligent dispatch module obtains real-time traffic information, including road congestion index, traffic speed, road closure information, etc. Traffic information is obtained in real time from a third-party service platform (such as a traffic monitoring center or a map service API) through an IoT device, and is correlated and analyzed with the vehicle's current location and destination data.

[0063] In this embodiment, the intelligent dispatch module obtains real-time traffic information, including road congestion index, traffic speed, road closure information, etc. Traffic information is obtained in real time from a third-party service platform (such as a traffic monitoring center or a map service API) through an IoT device, and is correlated and analyzed with the vehicle's current location and destination data.

[0064] Specifically, the traffic information is quantified as the congestion index (C traffic ), and its calculation formula is: in: L cong is the length of the congested part of the road section; L total is the total length of the road section.

[0065] The system uses the congestion index to determine the traffic conditions of the current road section and re-plans the vehicle's transportation route if necessary. As an option, if the congestion index of a section exceeds a preset threshold (such as 0.7), the system will automatically eliminate the section and look for an alternative route.

[0066] It should be noted that the dynamic adjustment of the transportation route is aimed at optimizing transportation efficiency, specifically minimizing transportation time (T route ) and transportation cost (C trans ). The objective function of the path optimization problem can be expressed as: min P (T route +α·C fuel +β·R empty ) in: P is a path in the candidate path set; T route Indicates the travel time of the vehicle on the path; C fuel represents the fuel consumption cost on the path; R empty It represents the empty driving rate, which is the ratio of the vehicle’s empty mileage to the total mileage; α and β are weight coefficients, which can be adjusted according to actual needs.

[0067] In one possible implementation, the system uses a reinforcement learning algorithm to dynamically optimize the scheduling strategy. Specifically, the reinforcement learning algorithm simulates various scenarios in the transportation process (such as traffic congestion, vehicle failure, etc.) to train the scheduling model's responsiveness to complex environments. The state update formula of the Q learning model is: Q(s,a)←Q(s,a)+α[r+γmax a′ Q(s′,a′)-Q(s,a)] in: s is the current transport status; a is the scheduling action taken by the system; r is the instant reward value, which indicates the degree of improvement in transportation efficiency after optimization; γ is the discount factor, which represents the weight of future rewards.

[0068] For example, in a logistics company's transportation scenario, the system detected that a vehicle was currently traveling on a congested road, with a congestion index of 0.8 and an estimated travel time of 30 minutes. The intelligent dispatching module replanned the route based on real-time traffic information, guided the vehicle to a more unobstructed alternative road, and reallocated subsequent transportation tasks based on the vehicle's load and task priority.

[0069] In the process of task allocation, the system gives priority to the vehicle's load condition (W load ) and the distance to the destination (D dest ). The goal of task allocation is to maximize load utilization while minimizing transportation distance. The objective function can be expressed as: in: W capacity is the total load capacity of the vehicle; D dest is the distance between the target location of the task and the current location of the vehicle.

[0070] As an option, the intelligent dispatch module can also combine historical transportation data to predictively adjust the vehicle's dispatch strategy. For example, when a vehicle's historical operating data shows that its transportation efficiency is low under high load conditions, the system will assign it lighter tasks to optimize overall transportation efficiency.

[0071] It should be understood that in order to ensure the real-time nature of the dispatching process, a data priority mechanism is also designed in this embodiment. For example, the update frequency of real-time traffic information is higher than that of historical data and environmental parameters to ensure the rapid response capability of dispatching decisions.

[0072] In another possible implementation, the intelligent scheduling module also supports large-scale task allocation across regions. Specifically, the system can reorganize tasks among multiple vehicles to reduce idle driving distance. For example, when the task demand in a certain area exceeds the processing capacity of the vehicle, the system will dynamically deploy vehicles from neighboring areas to enter the area to perform tasks.

[0073] In summary, this step significantly improves the transportation efficiency of vehicles and reduces transportation costs by combining the analysis of real-time traffic information with path planning algorithms and task allocation algorithms, providing an intelligent scheduling solution for complex transportation networks.

[0074] S5. Monitor the cargo status in real time through the cargo management module and generate an alarm signal in case of abnormal conditions; The solution of the present invention monitors the status of goods in real time through the cargo management module to ensure the safety and stability of the goods during transportation. This module collects key status data of the goods through the sensor network, including temperature, humidity, vibration, location and other information, and makes judgments based on the preset safety threshold. When the status of the goods is abnormal, an alarm signal is immediately generated and pushed to the management end. It should be noted that this step not only provides the ability to dynamically monitor the status of the goods, but also can quickly trigger an emergency response when an abnormality occurs, thereby reducing the risk of damage to the goods.

[0075] In this embodiment, the cargo management module collects cargo status information in real time through a multifunctional sensor network deployed in the transport vehicle. The monitoring parameters of the sensor include but are not limited to: Temperature (T h ): Used to monitor the temperature conditions of the cargo transportation environment, especially suitable for temperature control of refrigerated food or medicine in cold chain logistics; Humidity (H h ): Used to detect humidity changes in the transportation environment to ensure that humidity-sensitive goods (such as electronic products, paper products, etc.) are within a safe range; Vibration (V h ): Used to monitor whether the goods are subjected to abnormal vibration or collision during transportation; GPS location: Real-time record of cargo transportation track to ensure that cargo is transported according to the preset route.

[0076] As an option, the sensor network is connected to the central management system through an IoT communication module and transmits the collected status data at a preset frequency. For example, the collection frequency can be set to once a minute, or dynamically adjusted according to the category and sensitivity of the goods.

[0077] It should be noted that in order to improve the accuracy and reliability of data monitoring, the present invention adopts a mode combining distributed data collection and central analysis. Specifically, the sensor node performs preliminary processing on the raw data, such as filtering outliers and averaging sampling, and then uploads the processed data to the central analysis unit of the cargo management module.

[0078] In one possible implementation, the cargo management module analyzes the sensor data in real time and compares the monitored value with a preset safety threshold. For example, the temperature safety range can be set as [T min ,T max ], if the temperature value T is detected h If it exceeds this range, an alarm signal will be triggered immediately: Similarly, for humidity and vibration parameters, corresponding safety thresholds [H min ,Hmax ] and [V min ,V max ] If the detected value exceeds the safety range, a corresponding alarm message will be generated.

[0079] As an extension, after an abnormal alarm signal is generated, the cargo management module can also combine the vehicle location data to push the cargo's current geographic location, status parameters, and recommended emergency measures to the management system. For example, in cold chain transportation, when the temperature exceeds the safe range, the system can suggest that the driver increase the power of the cooling device, or directly adjust the transportation route to the nearest cold storage.

[0080] Specifically, in an exemplary implementation, the cargo management module introduces an anomaly detection model based on machine learning to analyze sensor data. For example, a support vector machine (SVM) is used to classify historical transportation data and real-time monitoring data to distinguish between normal and abnormal states. The decision function of SVM can be expressed as: f(x)=sign(w T x+b) Among them, x is the characteristic vector of the monitoring parameter, w is the weight vector, and b is the bias term. When f(x)<0, the system determines that the current state is abnormal.

[0081] In another possible implementation, the alarm mechanism of the cargo management module can be further subdivided into multiple levels of alarms. For example, according to the extent to which the monitoring value exceeds the safety range, the alarm level can be divided into three levels: low, medium, and high, and each level corresponds to different emergency response measures. For example: Low-level alarm: The temperature or humidity deviates slightly from the range, and the driver is only reminded to pay attention; Intermediate alarm: The deviation range is large, and it is recommended to adjust the transportation conditions or routes; Advanced alarm: If the deviation from the range is serious, the management center will be notified directly to take emergency measures.

[0082] It should be understood that the cargo management module in the present invention can also work in conjunction with other modules after generating an alarm signal. For example, an abnormal alarm can trigger the intelligent scheduling module to re-plan the transportation route, or notify the energy supply module to prioritize emergency supply for the vehicle.

[0083] As an option, in order to enhance the coverage of cargo status monitoring, the solution of the present invention supports the combined deployment of multiple sensor networks. For example, in long-distance transportation, embedded sensors can be added inside the cargo packaging to accurately monitor the status of each single piece of cargo, rather than being limited to the overall environmental parameters within the vehicle.

[0084] In summary, the present invention realizes real-time monitoring of cargo status and abnormal alarm through the cargo management module, and provides an effective technical means for safety protection during cargo transportation.

[0085] S6. Generate vehicle performance evaluation reports based on historical driving data, predict potential failures, and push maintenance recommendations.

[0086] The present invention builds a complete vehicle performance evaluation and maintenance suggestion generation system by comprehensively utilizing the vehicle's historical driving data, real-time status data, and big data analysis and prediction algorithms. It should be noted that the design purpose of this step is to discover potential failure risks in advance and push corresponding maintenance suggestions through scientific evaluation of the vehicle's health status, thereby improving the reliability and transportation efficiency of vehicle operation and reducing the risk of unplanned downtime.

[0087] In this embodiment, the historical driving data is collected from the vehicle monitoring module, and the data includes but is not limited to: Cumulative mileage (D total ) Average speed (V avg ) Fuel consumption record or electricity consumption record (C fuel or C elec ) Temperature anomaly count (such as the number of times the engine temperature exceeds the threshold) Fault code records (data from the OBD system, such as engine and brake system fault codes, etc.) These historical data are regularly uploaded to the big data platform through the IoT communication module between the vehicle and the cloud server and stored in a distributed database as input data for subsequent performance evaluation and prediction models.

[0088] Specifically, the core of vehicle performance evaluation is to generate a vehicle health index (HI) by analyzing historical driving data. The health index is a key indicator to measure the current health status of the vehicle, which is defined as: in: The accumulated losses are calculated based on key performance indicators (such as fuel efficiency, engine temperature, etc.) and fault records in historical operating data; The maximum allowable losses are determined by vehicle design parameters and industry standards.

[0089] As an option, in order to improve the calculation accuracy of the health index, the calculation of the loss value can be further subdivided into the cumulative loss of different components. For example, the engine loss, brake system loss and battery life loss are estimated separately based on the corresponding models.

[0090] It should be noted that the calculation results of the health index are divided into multiple levels, such as: good (HI>0.8), caution (0.5≤HI≤0.8) and warning (HI<0.5). When the health index is lower than the set threshold, the system will trigger the process of generating potential fault prediction and maintenance recommendations.

[0091] In one possible implementation, potential failure prediction is performed based on a machine learning model. For example, time series analysis (such as an ARIMA model) is used to predict the trend of key performance parameters. The prediction formula is: y t =c+φ 1 y t-1 +φ 2 y t-2 +…+φ p y t-p +∈ t in: y t is the performance parameter value at the current time; φ i is the model parameter, ∈ t is the noise term.

[0092] By modeling the historical trend of engine temperature, brake efficiency or fuel efficiency, it can predict its changes in the future and identify possible failure points. For example, if it is predicted that the engine temperature may exceed the safety threshold under high load conditions, it will be marked as a potential failure.

[0093] As an extension, the system can also use deep learning models (such as long short-term memory networks, LSTM) to process more complex historical data relationships and fault prediction. This approach is particularly suitable for capturing nonlinear relationships and long-term dependencies in time series.

[0094] For example, in a health assessment of a vehicle, its health index is calculated to be 0.45 (in warning state). The predictive model analysis shows that its fuel efficiency has gradually decreased in the last two months, and the cumulative service life of the brake pads is close to its design value. The system automatically generates maintenance recommendations, including replacing the brake pads and checking the injectors in the fuel system.

[0095] Maintenance recommendations are generated based on a combination of prediction results and the actual vehicle usage conditions. Specifically, the recommendations include: Parts that require maintenance; Recommended maintenance schedule; Recommended maintenance location (such as the nearest repair center or service station); List of replacement parts required and estimated costs.

[0096] As an option, the push method of maintenance suggestions can be diversified. For example, through the vehicle terminal display, mobile phone APP notification or directly sent to the vehicle management platform. At the same time, the system can dynamically optimize the recommended maintenance time and location based on the vehicle's transportation task situation.

[0097] It should be understood that the vehicle performance evaluation report in the solution of the present invention is not only used for fault prediction, but also can assist in transportation scheduling. For example, when scheduling task allocation, the system gives priority to assigning longer transportation tasks to vehicles with high health indexes, and arranges vehicles that need maintenance as spare vehicles.

[0098] In another possible implementation, the system also supports comprehensive evaluation of the performance of the entire fleet and generates a maintenance plan for the fleet. For example, based on the health index distribution of all vehicles and current mission requirements, the optimal fleet maintenance strategy is generated to maximize the overall operating efficiency of the fleet.

[0099] In summary, the present invention realizes the automatic generation of vehicle performance evaluation, potential fault prediction and maintenance suggestions through in-depth analysis of historical driving data, which not only effectively reduces the failure rate but also improves the operational reliability and efficiency during transportation.

[0100] A vehicle transportation management system based on digital technology, comprising: Vehicle monitoring module, used to collect vehicle energy status data in real time; In this embodiment, the vehicle monitoring module is used to collect the energy status data of the vehicle in real time, including but not limited to: Battery power (E b ) Fuel quantity (F t ) Engine temperature (T e ) Vehicle real-time geographic location (GPS coordinates) As an option, the acquisition unit of the vehicle monitoring module uses high-precision sensors (such as power sensors, fuel sensors, temperature sensors and GPS positioning modules) in conjunction with the data processing unit. The data processing unit reads the sensor signals at a preset sampling frequency and pre-processes the data. For example: The Kalman filter algorithm is used to denoise the collected energy status data, and the filtered energy status data is more stable and accurate; The remaining energy (E r =E b +F t ).

[0101] The collected data is transmitted to the IoT communication module through the local communication interface in the vehicle monitoring module for subsequent data analysis and decision support.

[0102] IoT communication module, used to transmit collected vehicle data to the big data platform; In this embodiment, the IoT communication module is responsible for uploading the data collected by the vehicle monitoring module to the big data platform in real time. As an implementation method, the communication module supports multiple wireless communication protocols, including but not limited to: 4G / 5G network: suitable for high-bandwidth and low-latency data transmission in urban areas; LoRa or NB-IoT protocol: low-power, long-distance data transmission suitable for remote areas.

[0103] Specifically, the communication module uses packet transmission technology to upload the collected data to the big data platform in encrypted form to ensure the security and integrity of the data during transmission. It should be noted that the communication module also includes a data buffer unit to temporarily store the collected data when the network is unstable, and to supplement the data through an incremental upload mechanism after the signal is restored.

[0104] Big data analysis module, used to analyze the energy status of the vehicle and generate replenishment warning signals; In this embodiment, the main functions of the big data analysis module include: Energy status analysis: The remaining energy (E r ) and the remaining travel time (T r ): Among them, C t is the real-time energy consumption rate of the vehicle.

[0105] Resupply warning signal generation: If the remaining driving time is lower than the set threshold (such as 30 minutes), the system generates a supply warning signal and pushes it to the intelligent scheduling module and management terminal.

[0106] As an extension, the big data analysis module also introduces time series analysis algorithms (such as the ARIMA model) to predict the changing trends of energy status, thereby achieving more accurate supply demand warnings.

[0107] Intelligent scheduling module, used to dynamically adjust transportation routes and task allocation based on real-time traffic information, vehicle status and transportation demand; In this embodiment, the intelligent scheduling module dynamically adjusts the transportation route and task allocation according to real-time traffic information, vehicle status and transportation demand. Its main functions include: Dynamic route planning: Based on real-time traffic data (such as road congestion index) and the distance to the destination, the intelligent scheduling module calculates the optimal transportation route through the A* algorithm. The objective function is: min P (T route +α·R empty ) Among them, T route is the travel time, R empty is the idle rate, and α is the weight parameter.

[0108] Task allocation optimization: Based on the vehicle's load capacity and task urgency, the intelligent scheduling module prioritizes tasks for vehicles with high resource utilization to reduce transportation costs.

[0109] Real-time scheduling adjustment: When the vehicle deviates from the scheduled route or the mission requirements change, the system updates the scheduling strategy and reallocates tasks through the reinforcement learning model.

[0110] Cargo management module, used to monitor the status of cargo and generate alarm signals when abnormalities occur; The cargo management module monitors the status of cargo in real time through a sensor network, including key parameters such as temperature, humidity, and vibration. In this embodiment: Temperature monitoring value (T h ) and humidity monitoring value (H h ) is collected by sensors. If it exceeds the preset safety range (such as [T min ,T max ]), the system immediately generates an alarm signal: Vibration monitoring parameters (V h ) is used to detect abnormal collisions during cargo transportation. When the vibration amplitude exceeds the threshold, an alarm is also triggered.

[0111] The alarm signal is pushed to the driver terminal or management system through the IoT communication module so that emergency measures can be taken in time.

[0112] Report generation module, used to generate vehicle performance evaluation reports based on historical data, predict failures and provide maintenance recommendations.

[0113] The report generation module generates performance evaluation reports based on the vehicle's historical driving data and predicts potential failures. Its functions include: Health Index Calculation: Calculate the vehicle health index (HI) using the formula: The accumulated losses are estimated from key performance parameters (such as fuel efficiency and engine temperature) from historical data.

[0114] Potential failure prediction: Use time series analysis models (such as ARIMA models) to predict the future status of key components. For example, if the predicted value of engine temperature is out of the safe range, the system will mark it as a potential failure.

[0115] Maintenance suggestion generation: Based on the prediction results, the system generates specific maintenance recommendations, including the parts that need to be replaced and the recommended maintenance time.

[0116] As an option, maintenance recommendations can be pushed to relevant personnel via vehicle terminals, management platforms or mobile applications.

[0117] Although embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that various changes, modifications, substitutions and variations may be made to the embodiments without departing from the principles and spirit of the present invention, and that the scope of the present invention is defined by the appended claims and their equivalents.

Claims

1. A vehicle transportation management method based on digital technology, characterized in that: The following steps are involved: Collect the vehicle's energy status data in real time through the vehicle monitoring module; Use IoT technology to transmit collected vehicle data to a big data platform, analyze the data, and generate early warning signals for energy status; When the warning signal is triggered, the optimal refueling route is determined based on the vehicle’s current location and traffic information, and energy refueling services are arranged in advance; Through the intelligent scheduling module, the transportation routes and task allocation of vehicles are dynamically adjusted according to real-time traffic information, vehicle load, and destination distance factors; The cargo management module monitors cargo status in real time and generates alarm signals in case of abnormal conditions; Generate vehicle performance evaluation reports based on historical driving data, predict potential failures, and push maintenance recommendations.

2. A vehicle transportation management method based on digital technology according to claim 1, characterized in that: The data collected by the vehicle monitoring module includes vehicle battery power, fuel level, engine temperature and geographic location information, and the data is transmitted to the big data platform at a predetermined frequency through the Internet of Things communication module.

3. The vehicle transportation management method based on digital technology according to claim 1 is characterized in that: The big data platform analyzes the vehicle energy status data, generates a replenishment warning signal by comparing the current remaining energy with a preset safety threshold, and calculates the optimal path to the replenishment station based on the vehicle's geographic location and traffic data.

4. The vehicle transportation management method based on digital technology according to claim 1 is characterized in that: The step of dynamically adjusting the vehicle transportation route and task allocation through the intelligent scheduling module includes: Calculate transportation time and empty driving rate based on real-time traffic information; Optimize routes to minimize transit time and empty trips, while taking into account vehicle load and distance to destination.

5. The vehicle transportation management method based on digital technology according to claim 1 is characterized in that: The cargo management module collects cargo status data in real time through the sensor network and sets a safety threshold. If the monitoring data exceeds the safety range, an abnormal alarm signal is generated and pushed to the management system.

6. The vehicle transportation management method based on digital technology according to claim 1 is characterized in that: The cargo management module monitors the transportation trajectory of the cargo in real time and generates an alarm message when the trajectory deviates from the preset path.

7. A vehicle transportation management system based on digital technology, a vehicle transportation management method based on digital technology according to any one of claims 1 to 6, characterized in that: include: Vehicle monitoring module, used to collect vehicle energy status data in real time; IoT communication module, used to transmit collected vehicle data to the big data platform; Big data analysis module, used to analyze the energy status of the vehicle and generate replenishment warning signals; Intelligent scheduling module, used to dynamically adjust transportation routes and task allocation based on real-time traffic information, vehicle status and transportation demand; Cargo management module, used to monitor the status of cargo and generate alarm signals when abnormalities occur; Report generation module, used to generate vehicle performance evaluation reports based on historical data, predict failures and provide maintenance recommendations.

8. The vehicle transportation management system based on digital technology according to claim 7 is characterized in that: The intelligent scheduling module optimizes transportation task allocation through a machine learning algorithm, which adjusts the scheduling strategy based on historical task allocation results and real-time transportation conditions.

9. The vehicle transportation management system based on digital technology according to claim 1 is characterized in that: The report generation module uses a time series analysis algorithm to analyze the historical vehicle driving data to predict potential failures of vehicle components and provide maintenance suggestions.

10. The vehicle transportation management system based on digital technology according to claim 1 is characterized in that: The vehicle monitoring module collects the energy status data of the vehicle through a high-precision sensor, and the data collection frequency of the sensor can be dynamically adjusted.

Images