A method, device, electronic device and storage medium for real-time management of transport vehicles

Abstract

The present invention discloses a real-time management method, device, electronic device and storage medium for transport vehicles, and relates to the technical field of vehicle transport management; a real-time management method for transport vehicles, firstly determines the area where the vehicle can travel, and determines the urgency of different transport vehicles through fuzzy logic through environmental data during vehicle transportation, vehicle driving coefficient and connection failure coefficient, and then calculates the important coefficients of different mesh nodes, and changes the driving routes of different vehicles in real time according to the actual position of the vehicle, the urgency of the vehicle and the important coefficient of the mesh node, and sends a notification to the corresponding vehicle. In this way, based on route planning for all transport vehicles, in complex transport scenarios, the overall transport efficiency can be effectively coordinated and optimized.

Description

Technical Field

[0001] The present invention belongs to the technical field of vehicle transportation management, and in particular relates to a method, device, electronic equipment and storage medium for real-time management of transportation vehicles. Background Art

[0002] Vehicle transportation management is a process of organizing, monitoring and optimizing vehicle transportation activities. It involves planning, scheduling, tracking and evaluating vehicle transportation tasks to ensure the effectiveness, safety and economy of transportation. When transporting goods, multiple transport vehicles are generally used to transport from the starting point to the end point, and multiple stops are set up on the route to provide some convenience for the driver and to understand the transportation of goods at the same time; at the same time, in order to make the vehicle transportation meet the requirements, a vehicle transportation monitoring system is generally established to monitor the status of the transport vehicle in real time while driving. When problems are found in the transport vehicle while driving, a signal is promptly sent to remind relevant personnel and adjustments are made to the vehicle's transportation route to ensure the effectiveness, safety and economy of transportation.

[0003] However, when adjusting the transportation route, traditional vehicle transportation monitoring systems often only plan a single route for vehicles that may have malfunctions. This single-vehicle route planning method has obvious limitations, especially in complex transportation scenarios that require simultaneous scheduling and optimization of multiple vehicles. Since the transportation status and location of each vehicle may be different, a planning strategy that only targets a single vehicle cannot effectively coordinate and optimize the overall transportation efficiency. Summary of the invention

[0004] The purpose of the present invention is to solve the problem that the planning strategy for only a single vehicle cannot effectively coordinate and optimize the overall transportation efficiency, and to propose a real-time management method, device, electronic device and storage medium for transportation vehicles.

[0005] In a first aspect of the implementation of the present invention, a method for real-time management of transport vehicles is first proposed, the method acts on a remote server, and the remote server is used to manage the transport vehicles in real time, wherein:

[0006] Obtaining an undirected road network graph corresponding to the transport area; the mesh nodes in the undirected road network graph are determined by temporary cargo unloading points and vehicle maintenance points; the routes in the undirected road network graph are determined by vehicle drivable routes;

[0007] Acquire connection data and vehicle driving data of several vehicles between the vehicles and the remote server during transportation, obtain a driving coefficient according to the vehicle driving data, and obtain a connection failure coefficient according to the connection data; the connection data includes a picture frame rate fluctuation value and a sound and picture different frequency coefficient; the vehicle driving data includes a vehicle fuel consumption rate and a driver fatigue coefficient;

[0008] Acquire environmental data during vehicle transportation, and determine the urgency of different transportation vehicles through fuzzy logic using the environmental data, the vehicle travel coefficient and the connection failure coefficient;

[0009] The importance coefficients of different mesh nodes are obtained according to the temporary cargo unloading point and the vehicle maintenance point, and the driving routes of different vehicles are changed in real time according to the actual positions of the vehicles, the urgency of the vehicles and the importance coefficients of the mesh nodes, and notifications are issued to the corresponding vehicles.

[0010] Optionally, obtaining connection data between a plurality of vehicles and a remote server during transportation includes:

[0011] The remote server obtains a real-time uploaded vehicle information video stream within a fixed time interval, extracts frame rate data from the video stream according to a fixed time length, and establishes a frame rate set, wherein the frame rate set includes a plurality of frame rate values;

[0012] Performing data cleaning on a plurality of frame rate values ​​in the frame rate set by using a moving average method to obtain a usable data set;

[0013] Decomposing the frame rate data in the data set using Daubechies wavelet to obtain approximate coefficients and detail coefficients of each layer, and obtaining the energy spectrum density of each layer through the approximate coefficients and detail coefficients;

[0014] The frame rate fluctuation value is calculated by weighted averaging method. The calculation method is to multiply the energy spectrum density of each layer by the weight of the corresponding layer number to obtain the weighted energy spectrum density, and then add the weighted energy spectrum density of each layer to obtain the frame rate fluctuation value.

[0015] Optionally, the connection data further includes:

[0016] The connection data also includes:

[0017] Obtain the video features and audio features sent by the remote server and received by the vehicle within a fixed time interval; initialize the distance matrix of the video features and audio features, where both the rows and columns have an initial value of 0;

[0018] Use a dynamic programming algorithm to fill in the rest of the distance matrix. The method of calculating the distance matrix is ​​to calculate the square of the difference between each audio feature and video feature, and add it to the minimum value of the three adjacent positions of top, left and top left to obtain the planning distance matrix;

[0019] According to the planning distance matrix, the best path from the upper left corner to the lower right corner is obtained, and the best path is the path that minimizes the total distance;

[0020] Obtain the corresponding audio features and video features on the optimal path, and calculate the sum of the absolute differences of each pair of corresponding feature values ​​to obtain the frequency difference;

[0021] The maximum number of elements in the video features and audio features is obtained as the maximum frequency, and the sound-image frequency coefficient is obtained by calculating the ratio of the frequency difference and the maximum frequency;

[0022] Obtaining a connection failure coefficient according to the connection data includes:

[0023] The picture frame rate fluctuation value and the sound-picture different frequency coefficient are weightedly summed to obtain a connection failure coefficient.

[0024] Optionally, obtaining a driving coefficient according to the vehicle driving data includes:

[0025] Obtain the actual vehicle fuel consumption in different time periods within a fixed time interval, and compare the actual vehicle fuel consumption in different time periods with the corresponding preset vehicle fuel consumption range. When the actual vehicle fuel consumption is not within the preset vehicle fuel consumption range, mark the time period as an abnormal time period; obtain the total number of time periods, and obtain the number of abnormal time periods in the total time period, and obtain the vehicle fuel consumption rate through the abnormal time periods and the total number of time periods;

[0026] In a fixed time interval, an infrared camera is used to capture a facial information image of the driver, and the facial information image is processed to obtain an actual breathing image, and the actual breathing image is compared with a preset normal breathing image to obtain a brightness deviation value, and the driver fatigue coefficient is obtained by matching the deviation value with a preset driver fatigue coefficient corresponding table;

[0027] The vehicle fuel consumption rate and the driver fatigue coefficient are weighted and summed to obtain the vehicle driving coefficient.

[0028] Optionally, obtaining environmental data during vehicle transportation, and determining the urgency of different transport vehicles by using the environmental data, the vehicle travel coefficient, and the connection failure coefficient through fuzzy logic includes:

[0029] Acquiring environmental data during vehicle transportation, the environmental data including freezing degree and particulate matter concentration;

[0030] The environmental data, the vehicle driving coefficient and the connection failure coefficient are defined as input variables and are respectively classified into different fuzzy sets;

[0031] The urgency of vehicle transportation is defined as the output variable and divided into fuzzy sets;

[0032] Formulate fuzzy rules to describe the impact of different input variables on output variables;

[0033] Fuzzy reasoning is performed based on fuzzy rules to output the transportation urgency of different vehicles.

[0034] Optionally, the important coefficients of different mesh nodes obtained according to the temporary cargo unloading point and the vehicle maintenance point include:

[0035] By presetting a temporary cargo unloading point level table and a vehicle maintenance point level table, the temporary cargo unloading point levels and vehicle maintenance point levels of different mesh nodes are obtained, and the temporary cargo unloading point levels and vehicle maintenance point levels of all mesh nodes are added together to obtain the level coefficients corresponding to all mesh nodes in the undirected road network graph;

[0036] Comparing the level coefficient with a preset first threshold, and when the level coefficient is not less than the preset first threshold, marking the mesh node as an important node;

[0037] Calculating the clustering coefficient of the important nodes in the undirected road network graph, and multiplying the level coefficient and the clustering coefficient of the important nodes to obtain the importance coefficient of the mesh node, and comparing the importance coefficient with a preset second threshold value, if the importance coefficient is not less than the preset second threshold value, marking the node as a must-pass node;

[0038] Changing the driving routes of different vehicles in real time and sending notifications to corresponding vehicles based on the actual location of the vehicle, the urgency of the vehicle and the importance coefficient of the mesh node include:

[0039] A network analysis algorithm is used to calculate the shortest path from the current position of the vehicle to the destination. The shortest path includes all the nodes that must be passed through. The shortest paths of different vehicles are compared to check whether there is path overlap and whether the overlap time point is consistent. For vehicles with path overlap and the overlap time point is consistent, the shortest path calculated by the vehicle with the highest urgency is given priority. At the same time, the shortest path is adjusted in sequence according to the urgency of the vehicle to ensure that vehicles with high urgency can be given priority. The adjusted path set forms the final driving path set, and the corresponding path in the driving path set is sent to the corresponding driving vehicle through the remote server.

[0040] In a second aspect of the present invention, a real-time management device for transport vehicles is provided, the device comprising:

[0041] Road network map acquisition module: obtain an undirected road network map corresponding to the transportation area; the mesh nodes in the undirected road network map are determined by temporary cargo unloading points and vehicle maintenance points; the routes in the undirected road network map are determined by vehicle drivable routes;

[0042] Data processing module: obtains connection data and vehicle driving data of several vehicles during transportation between the vehicles and the remote server, obtains a driving coefficient according to the vehicle driving data, and obtains a connection failure coefficient according to the connection data; the connection data includes a picture frame rate fluctuation value and a sound and picture different frequency coefficient; the vehicle driving data includes a vehicle fuel consumption rate and a driver fatigue coefficient;

[0043] Urgency determination module: obtains environmental data during vehicle transportation, and determines the urgency of different transport vehicles through fuzzy logic using the environmental data, the vehicle driving coefficient and the connection failure coefficient;

[0044] Notification module: obtains the importance coefficients of different mesh nodes according to the temporary cargo unloading point and the vehicle maintenance point, and changes the driving routes of different vehicles in real time according to the actual position of the vehicle, the urgency of the vehicle and the importance coefficients of the mesh nodes, and sends notifications to the corresponding vehicles.

[0045] In a third aspect of the present invention, an electronic device is provided, comprising a processor, a communication interface, a memory and a communication bus, wherein the processor, the communication interface and the memory communicate with each other via the communication bus;

[0046] Memory, used to store computer programs;

[0047] The processor is used to implement any of the above-mentioned method steps when executing the program stored in the memory.

[0048] In a fourth aspect of the implementation of the present invention, a computer-readable storage medium is provided, wherein a computer program is stored in the computer-readable storage medium, and when the computer program is executed by a processor, any of the method steps described above is implemented.

[0049] Beneficial effects of the present invention:

[0050] The present invention proposes a real-time management method for transport vehicles. The method first determines the area where the vehicle can travel, and determines the urgency of different transport vehicles through fuzzy logic using environmental data during vehicle transportation, vehicle driving coefficients and connection failure coefficients. The method then calculates the importance coefficients of different mesh nodes, and changes the driving routes of different vehicles in real time according to the actual positions of the vehicles, the urgency of the vehicles and the importance coefficients of the mesh nodes, and sends notifications to the corresponding vehicles. In this way, based on route planning for all transport vehicles, the overall transport efficiency can be effectively coordinated and optimized in complex transport scenarios. BRIEF DESCRIPTION OF THE DRAWINGS

[0051] The present invention will be further described below in conjunction with the accompanying drawings.

[0052] Figure 1A flow chart of a method for real-time management of transport vehicles is provided for an embodiment of the present invention;

[0053] Figure 2 A structural diagram of a transport vehicle real-time management device is provided for an embodiment of the present invention;

[0054] Figure 3 A schematic diagram of the structure of an electronic device provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0055] Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making any creative work shall fall within the scope of protection of the present invention.

[0056] The embodiment of the present invention provides a method for real-time management of transport vehicles. Figure 1 , Figure 1 This is a flow chart of a method for real-time management of transport vehicles provided by an embodiment of the present invention. The method acts on a remote server, and the remote server is used to manage transport vehicles in real time, wherein:

[0057] Obtain an undirected road network graph corresponding to the transport area; the mesh nodes in the undirected road network graph are determined by temporary cargo unloading points and vehicle maintenance points; the routes in the undirected road network graph are determined by vehicle drivable routes;

[0058] Acquire connection data between a number of vehicles and a remote server and vehicle driving data during transportation, obtain a driving coefficient according to the vehicle driving data, and obtain a connection failure coefficient according to the connection data;

[0059] Obtain environmental data during vehicle transportation, and use fuzzy logic to determine the urgency of different transport vehicles by combining environmental data, vehicle travel coefficients and connection failure coefficients;

[0060] The importance coefficients of different mesh nodes are obtained according to the temporary cargo unloading points and vehicle maintenance points, and the driving routes of different vehicles are changed in real time according to the actual positions of the vehicles, the urgency of the vehicles and the importance coefficients of the mesh nodes, and notifications are issued to the corresponding vehicles.

[0061] In one implementation method, the transportation area refers to the preset area where the vehicle can travel from the starting point to the end point; it should be noted that the reason for determining the transportation area is to more accurately control and manage the transportation activities of the vehicle, which not only helps to improve the efficiency of transportation, but also ensures that the vehicle travels within the preset path range, thereby reducing unnecessary route selection and possible risks of getting lost. At the same time, this also provides a clear framework for the transportation management system, enabling it to more effectively carry out path planning, vehicle scheduling and transportation monitoring.

[0062] In one implementation method, through the above steps, the area where the vehicle can travel is first determined, and the environmental data during vehicle transportation, the vehicle driving coefficient and the connection failure coefficient are used to determine the urgency of different transport vehicles through fuzzy logic, and then the important coefficients of different mesh nodes are calculated. According to the actual position of the vehicle, the urgency of the vehicle and the important coefficient of the mesh node, the driving routes of different vehicles are changed in real time and notifications are sent to the corresponding vehicles. In this way, route planning is carried out for all transport vehicles, and in complex transportation scenarios, the overall transportation efficiency can be effectively coordinated and optimized.

[0063] In one embodiment, obtaining connection data between a plurality of vehicles and a remote server during transportation, and obtaining a connection failure coefficient according to the connection data includes:

[0064] The remote server obtains the real-time uploaded vehicle information video stream within a fixed time interval, extracts frame rate data from the video stream according to a fixed time length, and establishes a frame rate set, which includes a plurality of frame rate values;

[0065] Perform data cleaning on several frame rate values ​​in the frame rate set by using the moving average method to obtain a usable data set;

[0066] In one implementation method, after extracting the frame rate data and establishing the frame rate set, more stable and accurate frame rate data can be obtained by applying the moving average method for data cleaning, thereby more effectively evaluating the quality and stability of the video stream. Such a cleaning process helps to improve the monitoring effect of the transportation management system on the vehicle transportation process.

[0067] Use Daubechies wavelet to decompose the frame rate data in the data set to obtain the approximate coefficient and detail coefficient of each layer, and then obtain the energy spectrum density of each layer through the approximate coefficient and detail coefficient;

[0068] The frame rate fluctuation value is calculated by weighted average method. The calculation method is to multiply the energy spectrum density of each layer by the weight of the corresponding layer number to obtain the weighted energy spectrum density, and then add the weighted energy spectrum density of each layer to obtain the frame rate fluctuation value.

[0069] In one implementation method, the frame rate fluctuation value calculated in this way uses Daubechies wavelet decomposition of frame rate data and weighted average method to calculate the energy spectrum density to obtain the frame rate fluctuation value method, which can accurately and comprehensively capture the multi-scale characteristics of the data and improve the robustness and adaptability of data processing. This calculation method not only accurately reflects the degree of frame rate fluctuation, but also has flexibility and real-time performance, providing strong data support for the transportation management system and contributing to system optimization and performance improvement.

[0070] Obtain the video features and audio features sent by the remote server and received by the vehicle within a fixed time interval; initialize the distance matrix of the video features and audio features, where both the rows and columns have an initial value of 0;

[0071] Use a dynamic programming algorithm to fill in the rest of the distance matrix. The method of calculating the distance matrix is ​​to calculate the square of the difference between each audio feature and video feature, and add it to the minimum value of the three adjacent positions of top, left and top left to obtain the planning distance matrix;

[0072] According to the planning distance matrix, the best path from the upper left corner to the lower right corner is obtained. The best path is the path that minimizes the total distance.

[0073] Obtain the corresponding audio features and video features on the optimal path, and calculate the sum of the absolute differences of each pair of corresponding feature values ​​to obtain the frequency difference;

[0074] The maximum number of elements in the video features and audio features is obtained as the maximum frequency, and the sound-image frequency coefficient is obtained by calculating the ratio of the frequency difference and the maximum frequency;

[0075] In one implementation method, the best matching path for audio and video features is calculated through a dynamic programming algorithm, which can effectively quantify the frequency difference between sound and picture, and reflect the correlation and difference between them through different frequency coefficients of sound and picture, providing an accurate and comprehensive analysis method for remote server analysis.

[0076] The picture frame rate fluctuation value and the sound-picture frequency difference coefficient are weightedly summed to obtain the connection failure coefficient.

[0077] In one implementation method, a connection failure coefficient is obtained by taking a weighted sum of the picture frame rate fluctuation value and the sound and picture different frequency coefficients. The connection relationship between the vehicle and the remote server can be judged by the specific value of the connection failure coefficient. The larger the connection failure coefficient is, the more unstable the connection between the vehicle and the remote server is, indicating that the driving condition of the vehicle is worse.

[0078] In one embodiment, obtaining the driving coefficient according to the vehicle driving data includes:

[0079] Obtain the actual vehicle fuel consumption in different time periods within a fixed time interval, and compare the actual vehicle fuel consumption in different time periods with the corresponding preset vehicle fuel consumption range. When the actual vehicle fuel consumption is not within the preset vehicle fuel consumption range, mark the time period as an abnormal time period; obtain the total number of time periods, and obtain the number of abnormal time periods in the total time period, and obtain the vehicle fuel consumption rate by the ratio of the abnormal time period to the total number of time periods;

[0080] In one implementation method, by comparing the actual vehicle fuel consumption with the preset range, abnormal time periods can be identified in a timely manner, making the calculated vehicle fuel consumption rate more accurate; it should be noted that the preset range refers to the preset range of vehicle fuel consumption, and the specific preset range is determined by specialized staff based on actual conditions and will not be elaborated here.

[0081] In a fixed time interval, the driver's facial information image is captured by an infrared camera, and the facial information image is processed to obtain an actual breathing image, and the actual breathing image is compared with a preset normal breathing image to obtain a brightness deviation value, and the driver's fatigue coefficient is obtained by matching the deviation value with a preset driver fatigue coefficient corresponding table;

[0082] In one implementation method, the driver's facial information image is captured by an infrared camera, and then analyzed to obtain the driver's fatigue coefficient. This method provides a more accurate fatigue assessment. At the same time, the infrared camera provides a non-invasive assessment method that does not affect the driver's driving experience. This facial image-based calculation method provides an objective fatigue assessment standard, reducing human judgment and subjective errors. The driver's fatigue coefficient calculated by this calculation method is more accurate.

[0083] The vehicle driving coefficient is obtained by weighted summing the vehicle fuel consumption rate and the driver fatigue coefficient.

[0084] In one implementation, a vehicle driving coefficient is obtained more accurately by taking a weighted sum of the vehicle fuel consumption rate and the driver fatigue coefficient.

[0085] In one embodiment, the environmental data of the vehicle during transportation is obtained, and the urgency of different transportation vehicles is determined by fuzzy logic using the environmental data, the vehicle driving coefficient and the connection failure coefficient.

[0086] Obtain environmental data during vehicle transportation, including freezing degree and particulate matter concentration;

[0087] Environmental data, vehicle travel coefficient and connection failure coefficient are defined as input variables and classified into different fuzzy sets respectively;

[0088] The urgency of vehicle transportation is defined as the output variable and divided into fuzzy sets;

[0089] Formulate fuzzy rules to describe the impact of different input variables on output variables;

[0090] Fuzzy reasoning is performed based on fuzzy rules to output the transportation urgency of different vehicles.

[0091] In one implementation, the degree of freezing and the concentration of particulate matter on the road surface on which different vehicles travel during transportation also affect the urgency of transportation by different vehicles;

[0092] Degree of ice: The degree of ice on the road has a direct impact on the vehicle's traction and grip. Driving on frozen roads increases the risk of vehicle skidding and loss of control, especially when turning or braking. Therefore, when the degree of ice on the road is high, the vehicle needs to drive more cautiously, the speed may be reduced, and the driving route may need to be adjusted, which will increase the time and risk of transportation, and therefore increase the urgency.

[0093] Particle concentration: Road sections with high particle concentration (such as dust, sand, etc.) may affect the vehicle's sight and air quality. When the particle concentration is high, the driver's visibility may be reduced, resulting in increased driving risks. In addition, high concentrations of particles may affect the vehicle's engine and filtration system, reducing the vehicle's performance and efficiency, and thus affecting the smooth progress of transportation. Therefore, on sections with high particle concentrations, vehicles need to drive more carefully and may need to increase the frequency of maintenance and cleaning, which will also increase the urgency of transportation.

[0094] Different vehicles may travel the same route, but due to different travel times, the degree of freezing of the surrounding road surface and the concentration of particulate matter may also be different when traveling on the same route, which will also affect the urgency of vehicle transportation.

[0095] In one implementation method, it should be noted that the division of fuzzy sets can be adjusted according to actual conditions, and environmental data, vehicle driving coefficient, connection failure coefficient, and transportation urgency can be divided into more than three sets, making the vehicle urgency division more refined.

[0096] In one implementation, the urgency of different transport vehicles is determined by fuzzy logic, taking into account the environmental data during vehicle transportation, the vehicle driving coefficient and the connection failure coefficient. The obtained transport urgency is comprehensive, flexible and accurate. This method can automatically provide personalized urgency assessment and respond to vehicle transportation status in real time, thereby improving decision-making efficiency, transportation efficiency and safety.

[0097] In one embodiment, the important coefficients of different mesh nodes obtained according to the cargo temporary unloading point and the vehicle maintenance point include:

[0098] By presetting the temporary cargo unloading point level table and the vehicle maintenance point level table, the temporary cargo unloading point levels and the vehicle maintenance point levels of different mesh nodes are obtained, and the temporary cargo unloading point levels and the vehicle maintenance point levels of all mesh nodes are added together to obtain the level coefficients corresponding to all mesh nodes in the undirected road network graph;

[0099] Comparing the level coefficient with a preset first threshold, when the level coefficient is not less than the preset first threshold, marking the mesh node as an important node;

[0100] In one implementation method, the first threshold is a threshold pre-designed for the level coefficient, and the specific value of the first threshold can be set by technical personnel based on experience; all mesh nodes in the undirected road network graph are first divided for the first time through the level coefficient, which can further manage and dispatch transport vehicles and improve transportation efficiency.

[0101] Calculate the clustering coefficient of the important nodes in the undirected road network graph, and multiply the level coefficient and the clustering coefficient of the important nodes to obtain the importance coefficient of the mesh node, and compare the importance coefficient with the preset second threshold value. If the importance coefficient is not less than the preset second threshold value, mark the node as a must-pass node;

[0102] In one implementation method, the clustering coefficient of the important nodes is calculated, and the level coefficient and the clustering coefficient of the important nodes are multiplied to obtain the importance coefficient of the mesh node, and the importance coefficient is compared with a preset second threshold. If the importance coefficient is not less than the preset second threshold, the node is marked as a must-pass node. The must-pass nodes calculated in this way are more representative and critical based on a comprehensive evaluation of the importance coefficient and the clustering coefficient, which can ensure that the path planning is more accurate and reasonable.

[0103] It should be noted that the must-pass nodes are the nodes that the transport vehicles must pass through during the transportation process. Although there are many nodes in the undirected road network graph, the must-pass nodes are more key decision points in the entire transportation process. When vehicles pass through these must-pass nodes, they can not only inspect or repair the vehicle itself, but also better and more effectively monitor the transportation status and transportation safety of the vehicle. Therefore, some nodes must be passed.

[0104] Changing the driving routes of different vehicles in real time and sending notifications to corresponding vehicles based on the actual location of the vehicle, the urgency of the vehicle and the importance coefficient of the mesh node include:

[0105] A network analysis algorithm is used to calculate the shortest path from the vehicle's current location to the destination. The shortest path includes all the nodes that must be passed through. The shortest paths of different vehicles are compared to check whether there is any path overlap and whether the overlap time points are consistent. For vehicles with overlapping paths and consistent overlap time points, the shortest path calculated by the vehicle with the highest urgency is given priority. At the same time, the shortest paths are adjusted in sequence according to the urgency of the vehicles to ensure that vehicles with high urgency can be given priority. The adjusted path set forms the final driving path set, and the corresponding paths in the driving path set are sent to the corresponding driving vehicles through the remote server.

[0106] In one implementation, the corresponding driving routes of different vehicles planned in this way can be accurately planned according to actual conditions, and in complex transportation scenarios, the overall transportation efficiency can be effectively coordinated and optimized.

[0107] Based on the same inventive concept, the embodiment of the present invention also provides a real-time management device for transport vehicles. Figure 2 , Figure 2 A schematic diagram of a real-time management device for transport vehicles provided by an embodiment of the present invention, the device comprising:

[0108] Road network map acquisition module: obtain the undirected road network map corresponding to the transportation area; the mesh nodes in the undirected road network map are determined by the temporary unloading points of goods and the vehicle maintenance points; the routes in the undirected road network map are determined by the drivable routes of the vehicles;

[0109] Data processing module: obtains the connection data and vehicle driving data of several vehicles during transportation between the vehicles and the remote server, obtains the driving coefficient according to the vehicle driving data, and obtains the connection failure coefficient according to the connection data; the connection data includes the picture frame rate fluctuation value and the sound and picture different frequency coefficient; the vehicle driving data includes the vehicle fuel consumption rate and the driver fatigue coefficient;

[0110] Urgency determination module: obtains environmental data during vehicle transportation, and uses fuzzy logic to determine the urgency of different transport vehicles using environmental data, vehicle driving coefficients, and connection failure coefficients;

[0111] Notification module: Obtain the importance coefficients of different mesh nodes based on the temporary unloading points of goods and the vehicle maintenance points, and change the driving routes of different vehicles in real time according to the actual positions of the vehicles, the urgency of the vehicles and the importance coefficients of the mesh nodes, and send notifications to the corresponding vehicles.

[0112] The embodiment of the present invention further provides an electronic device, such as Figure 3 As shown, it includes a processor 301, a communication interface 302, a memory 303 and a communication bus 304, wherein the processor 301, the communication interface 302, and the memory 303 communicate with each other through the communication bus 304.

[0113] Memory 303, used for storing computer programs;

[0114] The processor 301 is used to execute the program stored in the memory 303 to implement the following steps:

[0115] Obtain an undirected road network graph corresponding to the transport area; the mesh nodes in the undirected road network graph are determined by temporary cargo unloading points and vehicle maintenance points; the routes in the undirected road network graph are determined by vehicle drivable routes;

[0116] Acquire the connection data and vehicle driving data of several vehicles during transportation between the vehicles and the remote server, obtain the driving coefficient according to the vehicle driving data, and obtain the connection failure coefficient according to the connection data; the connection data includes the picture frame rate fluctuation value and the sound and picture different frequency coefficient; the vehicle driving data includes the vehicle fuel consumption rate and the driver fatigue coefficient;

[0117] Obtain environmental data during vehicle transportation, and use fuzzy logic to determine the urgency of different transport vehicles by combining environmental data, vehicle travel coefficients and connection failure coefficients;

[0118] The importance coefficients of different mesh nodes are obtained according to the temporary cargo unloading points and vehicle maintenance points, and the driving routes of different vehicles are changed in real time according to the actual positions of the vehicles, the urgency of the vehicles and the importance coefficients of the mesh nodes, and notifications are issued to the corresponding vehicles.

[0119] The communication bus mentioned in the above electronic device can be a Peripheral Component Interconnect (PCI) bus or an Extended Industry Standard Architecture (EISA) bus, etc. The communication bus can be divided into an address bus, a data bus, a control bus, etc. For ease of representation, only one thick line is used in the figure, but it does not mean that there is only one bus or one type of bus.

[0120] The communication interface is used for communication between the above electronic device and other devices.

[0121] The memory may include a random access memory (RAM) or a non-volatile memory (NVM), such as at least one disk memory. Optionally, the memory may also be at least one storage device located away from the aforementioned processor.

[0122] The above-mentioned processor can be a general-purpose processor, including a central processing unit (CPU), a network processor (NP), etc.; it can also be a digital signal processor (DSP), an application specific integrated circuit (ASIC), a field programmable gate array (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components.

[0123] In another embodiment provided by the present invention, a computer-readable storage medium is also provided, in which a computer program is stored. When the computer program is executed by a processor, the steps of any one of the above-mentioned methods for real-time management of transport vehicles are implemented.

[0124] In another embodiment provided by the present invention, a computer program product including instructions is also provided, which, when executed on a computer, enables the computer to execute any one of the methods for real-time management of transport vehicles in the above embodiments.

[0125] The above is a detailed description of an embodiment of the present invention, but the content is only a preferred embodiment of the present invention and cannot be considered to limit the scope of implementation of the present invention. All equivalent changes and improvements made within the scope of the present invention should still fall within the scope of the patent coverage of the present invention.

Claims

1. A real-time management method for transport vehicles, characterized in that: The method acts on a remote server, which is used to manage transport vehicles in real time, wherein: Obtaining an undirected road network graph corresponding to the transport area; the mesh nodes in the undirected road network graph are determined by temporary cargo unloading points and vehicle maintenance points; the routes in the undirected road network graph are determined by vehicle drivable routes; Acquire connection data and vehicle driving data of several vehicles between the vehicles and the remote server during transportation, obtain a vehicle driving coefficient according to the vehicle driving data, and obtain a connection failure coefficient according to the connection data; the connection data includes a picture frame rate fluctuation value and a sound and picture different frequency coefficient; the vehicle driving data includes a vehicle fuel consumption rate and a driver fatigue coefficient; Acquire environmental data during vehicle transportation, and determine the urgency of different transportation vehicles through fuzzy logic using the environmental data, the vehicle travel coefficient and the connection failure coefficient; The important coefficients of different mesh nodes are obtained according to the temporary cargo unloading point and the vehicle maintenance point, including: By presetting a temporary cargo unloading point level table and a vehicle maintenance point level table, the temporary cargo unloading point levels and vehicle maintenance point levels of different mesh nodes are obtained, and the temporary cargo unloading point levels and vehicle maintenance point levels of all mesh nodes are added together to obtain the level coefficients corresponding to all mesh nodes in the undirected road network graph; Comparing the level coefficient with a preset first threshold, and when the level coefficient is not less than the preset first threshold, marking the mesh node as an important node; Calculating the clustering coefficient of the important nodes in the undirected road network graph, and multiplying the level coefficient and the clustering coefficient of the important nodes to obtain the importance coefficient of the mesh node, and comparing the importance coefficient with a preset second threshold value, if the importance coefficient is not less than the preset second threshold value, marking the node as a must-pass node; According to the actual position of the vehicle, the urgency of the vehicle and the importance coefficient of the mesh node, the driving routes of different vehicles are changed in real time and notifications are sent to the corresponding vehicles, including: A network analysis algorithm is used to calculate the shortest path from the current position of the vehicle to the destination. The shortest path includes all the nodes that must be passed through. The shortest paths of different vehicles are compared to check whether there is path overlap and whether the overlap time point is consistent. For vehicles with path overlap and the overlap time point is consistent, the shortest path calculated by the vehicle with the highest urgency is given priority. At the same time, the shortest path is adjusted in sequence according to the urgency of the vehicle to ensure that vehicles with high urgency can be given priority. The adjusted path set forms the final driving path set, and the corresponding path in the driving path set is sent to the corresponding driving vehicle through the remote server.

2. A method for real-time management of transport vehicles according to claim 1, characterized in that: Acquiring the connection data between several vehicles and the remote server during transportation includes: The remote server obtains a real-time uploaded vehicle information video stream within a fixed time interval, extracts frame rate data from the video stream according to a fixed time length, and establishes a frame rate set, wherein the frame rate set includes a plurality of frame rate values; Performing data cleaning on a plurality of frame rate values ​​in the frame rate set by using a moving average method to obtain a usable data set; Decomposing the frame rate data in the data set using Daubechies wavelet to obtain approximate coefficients and detail coefficients of each layer, and obtaining the energy spectrum density of each layer through the approximate coefficients and detail coefficients; The frame rate fluctuation value is calculated by weighted averaging method. The calculation method is to multiply the energy spectrum density of each layer by the weight of the corresponding layer number to obtain the weighted energy spectrum density, and then add the weighted energy spectrum density of each layer to obtain the frame rate fluctuation value.

3. A method for real-time management of transport vehicles according to claim 2, characterized in that: The connection data also includes: Obtain the video features and audio features sent by the remote server and received by the vehicle within a fixed time interval; initialize the video features and audio features, and create a distance matrix, in which both rows and columns have an initial value of 0; Use a dynamic programming algorithm to fill in the rest of the distance matrix. The method of calculating the distance matrix is ​​to calculate the square of the difference between each audio feature and video feature, and add it to the minimum value of the three adjacent positions of top, left and top left to obtain the planning distance matrix; According to the planning distance matrix, the best path from the upper left corner to the lower right corner is obtained, and the best path is the path that minimizes the total distance; Obtain the corresponding audio features and video features on the optimal path, and calculate the sum of the absolute differences of each pair of corresponding feature values ​​to obtain the frequency difference; The maximum number of elements in the video features and audio features is obtained as the maximum frequency, and the sound-image frequency coefficient is obtained by calculating the ratio of the frequency difference and the maximum frequency; Obtaining a connection failure coefficient according to the connection data includes: The picture frame rate fluctuation value and the sound-picture different frequency coefficient are weightedly summed to obtain a connection failure coefficient.

4. A method for real-time management of transport vehicles according to claim 1, characterized in that: The vehicle driving coefficient obtained according to the vehicle driving data includes: Obtain the actual vehicle fuel consumption in different time periods within a fixed time interval, and compare the actual vehicle fuel consumption in different time periods with the corresponding preset vehicle fuel consumption range. When the actual vehicle fuel consumption is not within the preset vehicle fuel consumption range, mark the time period as an abnormal time period; obtain the total number of time periods, and obtain the number of abnormal time periods in the total time period, and obtain the vehicle fuel consumption rate through the abnormal time periods and the total number of time periods; In a fixed time interval, an infrared camera is used to capture a facial information image of the driver, and the facial information image is processed to obtain an actual breathing image, and the actual breathing image is compared with a preset normal breathing image to obtain a brightness deviation value, and the driver fatigue coefficient is obtained by matching the deviation value with a preset driver fatigue coefficient corresponding table; The vehicle fuel consumption rate and the driver fatigue coefficient are weighted and summed to obtain the vehicle driving coefficient.

5. A real-time management method for transport vehicles according to claim 1, characterized in that: Acquiring environmental data during vehicle transportation, and determining the urgency of different transport vehicles by using the environmental data, the vehicle travel coefficient and the connection failure coefficient through fuzzy logic includes: Acquiring environmental data during vehicle transportation, the environmental data including freezing degree and particulate matter concentration; The environmental data, the vehicle driving coefficient and the connection failure coefficient are defined as input variables and are respectively classified into different fuzzy sets; The urgency of vehicle transportation is defined as the output variable and divided into fuzzy sets; Formulate fuzzy rules to describe the impact of different input variables on output variables; Fuzzy reasoning is performed based on fuzzy rules to output the transportation urgency of different vehicles.

6. A real-time management device for transport vehicles, characterized in that: The device comprises: Road network map acquisition module: obtain an undirected road network map corresponding to the transportation area; the mesh nodes in the undirected road network map are determined by temporary cargo unloading points and vehicle maintenance points; the routes in the undirected road network map are determined by vehicle drivable routes; Data processing module: obtains connection data and vehicle driving data of several vehicles during transportation between the vehicles and the remote server, obtains the vehicle driving coefficient according to the vehicle driving data, and obtains the connection failure coefficient according to the connection data; the connection data includes the picture frame rate fluctuation value and the sound and picture different frequency coefficient; the vehicle driving data includes the vehicle fuel consumption rate and the driver fatigue coefficient; Urgency determination module: obtains environmental data during vehicle transportation, and determines the urgency of different transport vehicles through fuzzy logic using the environmental data, the vehicle driving coefficient and the connection failure coefficient; Notification module: Obtaining important coefficients of different mesh nodes according to the temporary cargo unloading point and the vehicle maintenance point, including: By presetting a temporary cargo unloading point level table and a vehicle maintenance point level table, the temporary cargo unloading point levels and vehicle maintenance point levels of different mesh nodes are obtained, and the temporary cargo unloading point levels and vehicle maintenance point levels of all mesh nodes are added together to obtain the level coefficients corresponding to all mesh nodes in the undirected road network graph; Comparing the level coefficient with a preset first threshold, and when the level coefficient is not less than the preset first threshold, marking the mesh node as an important node; Calculating the clustering coefficient of the important nodes in the undirected road network graph, and multiplying the level coefficient and the clustering coefficient of the important nodes to obtain the importance coefficient of the mesh node, and comparing the importance coefficient with a preset second threshold value, if the importance coefficient is not less than the preset second threshold value, marking the node as a must-pass node; According to the actual position of the vehicle, the urgency of the vehicle and the importance coefficient of the mesh node, the driving routes of different vehicles are changed in real time and notifications are sent to the corresponding vehicles, including: A network analysis algorithm is used to calculate the shortest path from the current position of the vehicle to the destination. The shortest path includes all the nodes that must be passed through. The shortest paths of different vehicles are compared to check whether there is path overlap and whether the overlap time point is consistent. For vehicles with path overlap and the overlap time point is consistent, the shortest path calculated by the vehicle with the highest urgency is given priority. At the same time, the shortest path is adjusted in sequence according to the urgency of the vehicle to ensure that vehicles with high urgency can be given priority. The adjusted path set forms the final driving path set, and the corresponding path in the driving path set is sent to the corresponding driving vehicle through the remote server.

7. An electronic device, characterized in that: It includes a processor, a communication interface, a memory and a communication bus, wherein the processor, the communication interface and the memory communicate with each other through the communication bus; Memory, used to store computer programs; A processor, for implementing the method steps described in any one of claims 1 to 5 when executing a program stored in a memory.

8. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the method according to any one of claims 1 to 5 is implemented.

Images