Management method and system for logistics transportation vehicles

Abstract

The invention discloses a management method and system for a logistics transportation vehicle, and relates to the technical field of logistics management, and the method comprises the steps: collecting the operation state data and vehicle driving behavior data of the logistics vehicle in real time, carrying out the multi-source heterogeneous data fusion and standardization processing of the collected data, and obtaining the preprocessing data; constructing a driving risk index model based on the preprocessed data, and determining a driver driving risk level based on the driving risk index model; and performing safety management on the driver based on the driver driving risk level. According to the invention, the running state of the logistics vehicle and the data of the vehicle driving behavior are monitored in real time, the running track and the safety behavior data of the transport vehicle are obtained, the running situation of the vehicle is sensed comprehensively, the vehicle-mounted dynamic monitoring device is fully utilized to strengthen the daily supervision of the truck, and the normal work and effective monitoring of the vehicle-mounted dynamic monitoring device are ensured.

Description

Technical Field

[0001] The present invention relates to the technical field of logistics management, and in particular to a management method and system for logistics transportation vehicles. Background Art

[0002] At present, there is a lack of digital management methods in the tracking and supervision of logistics vehicles and the management of transportation enterprises. The supervision of logistics and transportation vehicles is not in place, the efficiency of transportation scheduling is low, and tracking is difficult, resulting in unnecessary waste of transportation resources and increased transportation costs. At the same time, the various business systems in the logistics and transportation sectors of enterprises are relatively isolated, information cannot be effectively communicated, there are information islands, and there is a lack of a unified logistics and transportation information platform, resulting in inadequate supervision of logistics vehicles, low efficiency of transportation scheduling, and tracking difficulties. Summary of the Invention

[0003] The technical problem to be solved by the present invention is to overcome the shortcomings of the prior art and provide a management method and system for logistics transportation vehicles.

[0004] In order to solve the above technical problems, the technical solutions of the present invention are as follows: A management method for logistics transportation vehicles, comprising: Real-time collection of logistics vehicle operation status data and vehicle driving behavior data, Perform multi-source heterogeneous data fusion and standardization on the collected data to obtain pre-processed data; Building a driving risk index model based on the preprocessed data, and determining the driver's driving risk level based on the driving risk index model; Carry out safety management of drivers based on their driving risk levels.

[0005] As a preferred solution of the management method for logistics transportation vehicles described in the present invention, the vehicle's operating status data includes vehicle positioning data, vehicle operating trajectory data, vehicle operating speed, comprehensive OBD diagnostic data, vehicle energy consumption data, and vehicle maintenance data; the vehicle driving behavior data includes driving process video data.

[0006] As a preferred embodiment of the method for managing logistics transport vehicles according to the present invention, the method of determining the driver's driving risk level based on the driving risk index model includes: Determine the driver's driving risk score based on the driving risk index model; determining a driver's driving risk level based on the driver's driving risk score; Among them, the driving risk score is set to be less than 30 points as the first driving risk level; Set the driving risk score to be greater than or equal to 30 points and less than 50 points as the second driving risk level; The third driving risk level is set as a driving risk score greater than or equal to 50 points and less than 70 points; The fourth driving risk level is set as a driving risk score greater than or equal to 70 points and less than 90 points; A driving risk score greater than 90 is set as the fifth driving risk level.

[0007] As a preferred embodiment of the method for managing logistics transport vehicles according to the present invention, the safety management of the driver based on the driver's driving risk level includes: Limited dispatching authority is granted to drivers in the first driving risk level; Add a voice safety reminder system for drivers in the second driving risk level; For drivers in the third driving risk level, vehicles used by them must be connected to the co-pilot assistance system; Drivers in the fourth driving risk level will be suspended from dispatching and given safety training; The driving qualification reaffirmation mechanism will be activated for drivers who are in the fifth driving risk level.

[0008] As a preferred embodiment of the method for managing logistics transport vehicles of the present invention, after the driver safety management is performed based on the driver's driving risk level, the method further includes: A vehicle health index model is constructed based on the preprocessed data, and a vehicle health level is determined based on the vehicle health index model, and safety management of the vehicle is performed based on the vehicle health level.

[0009] As a preferred solution of the management method for logistics transportation vehicles of the present invention, the determination of the vehicle health level based on the vehicle health index model includes: determining a vehicle health score based on a vehicle health index model; determining a vehicle health rating based on the vehicle health score; The vehicle health level includes a first health level, a second health level and a third health level.

[0010] As a preferred embodiment of the method for managing logistics transport vehicles according to the present invention, the vehicle safety management based on the vehicle health level includes: Vehicles of the first health level will be given priority in long-distance trunk transport tasks, vehicles of the second health level will be given priority in short-distance cargo collection tasks, and vehicles of the third health level will be maintained.

[0011] As a preferred embodiment of the method for managing logistics transportation vehicles of the present invention, after constructing a vehicle health index model based on preprocessed data, determining a vehicle health level based on the vehicle health index model, and performing safety management of the vehicle based on the vehicle health level, the method further includes: A driving risk prediction model is constructed based on the preprocessed data, driving risk behaviors are predicted through the driving risk prediction model, and risk warning and disposal are carried out based on driving risk behaviors.

[0012] The present invention also provides a management system for logistics transportation vehicles, comprising: Data acquisition module, used to collect real-time operation status data and driving behavior data of logistics vehicles; The data processing module is used to perform multi-source heterogeneous data fusion and standardization on the collected data to obtain pre-processed data; A first model building module is used to build a driving risk index model based on the preprocessed data, and determine the driver's driving risk level based on the driving risk index model; The first safety management module is used to perform safety management on the driver based on the driver's driving risk level.

[0013] As a preferred solution of the management system for logistics transportation vehicles described in the present invention, it also includes: a second model building module, configured to build a vehicle health index model based on the preprocessed data, determine a vehicle health grade based on the vehicle health index model, and perform safety management on the vehicle based on the vehicle health grade; The third model building module is used to build a driving risk prediction model based on the preprocessed data, predict driving risk behavior through the driving risk prediction model, and perform risk warning and disposal based on the driving risk behavior.

[0014] The beneficial effects of the present invention are: (1) The present invention monitors the operating status and driving behavior data of logistics vehicles in real time, obtains the operating trajectory and safety behavior data of transport vehicles, comprehensively perceives the vehicle operating status, and realizes the macro-control of the operating status of all vehicles in a visual manner. It makes full use of the on-board dynamic monitoring device to strengthen the daily supervision of trucks and ensure that the on-board dynamic monitoring device works normally and the monitoring is effective.

[0015] (2) The present invention establishes a data analysis model, deeply mines data features, and transforms raw data resources into a basis for guiding decision-making, realizing waybill flow analysis, cargo volume analysis, popular transportation route analysis, non-site violation behavior time domain analysis, emergency response analysis, etc., providing support for the intelligent analysis of trucks, locomotives and construction machinery vehicles. On the basis of realizing safe vehicle transportation, the goal of efficiently dispatching trucks, locomotives and construction machinery vehicles is achieved through reasonable planning of transportation routes.

[0016] (3) The present invention realizes real-time monitoring of the operating dynamics of freight cars, locomotives, construction machinery vehicles and drivers through functions such as daily safety supervision, key area supervision and risk management, and realizes intelligent analysis and assessment of risk warnings. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative labor.

[0018] Figure 1 A schematic diagram of the flow chart of the method for managing logistics transport vehicles provided by the present invention; Figure 2 A schematic diagram of risk warning and disposal in the management method for logistics transportation vehicles provided by the present invention; Figure 3 This is a schematic diagram of the management system for logistics transportation vehicles provided by the present invention. DETAILED DESCRIPTION

[0019] In order to make the contents of the present invention more clearly understood, the present invention is further described below in detail based on specific implementation methods in conjunction with the accompanying drawings.

[0020] Figure 1 This is a flow chart of a method for managing logistics transport vehicles provided in an embodiment of the present application. The method specifically includes the following steps: Step S101: Collect the operation status data and vehicle driving behavior data of logistics vehicles in real time.

[0021] Specifically, the collected operation status data of logistics vehicles include vehicle positioning data, vehicle operation trajectory data, vehicle operation speed, comprehensive OBD diagnostic data, vehicle energy consumption data, and vehicle maintenance data.

[0022] The collected vehicle driving behavior data includes video data of the driver's driving process. The video data can be used to obtain the driver's driving behavior and driving habits, such as the number of times the driver drives fatigued and the duration of fatigue driving.

[0023] Step S102: performing multi-source heterogeneous data fusion and standardization processing on the collected data to obtain pre-processed data.

[0024] Specifically, ETL (Extract-Transform-Load) technology is used to cleanse and standardize heterogeneous data generated by systems such as GPS positioning, OBD onboard diagnostics, and ADAS. By formulating the "Logistics Vehicle Data Governance Specification," key parameters such as timestamps, coordinate systems, and data formats are standardized, creating a standardized data lake encompassing 128 metrics, including vehicle location (longitude / latitude / elevation), motion status (speed / acceleration / steering angle), and driving behavior (sudden braking / fatigue / distraction). This achieves a data cleansing accuracy rate of 99.7%.

[0025] Simultaneously, the Flink stream processing engine performs real-time feature extraction on over 5,000 pieces of dynamic data per second. Using sliding time windows (5-minute window size, 1-minute step length), 17 dynamic indicators, including vehicle trajectory deviation and driving behavior risk index, are calculated. Combined with the Kalman filter algorithm to eliminate positioning drift errors, trajectory restoration accuracy is improved to 0.5 meters. A driver behavior profiling model is developed, constructing a 32-dimensional feature vector based on operation frequency, force, and habits, enabling quantitative assessment of driving style.

[0026] Step S103: constructing a driving risk index model based on the preprocessed data, and determining the driver's driving risk level based on the driving risk index model.

[0027] Specifically, based on the pre-processed data obtained in the above steps, a driving risk index model is constructed, integrating 23 behavioral characteristics such as steering wheel grip, frequency of sudden acceleration, and fatigue driving duration to establish a five-level driver driving risk level. Among them, the driver's driving risk level is determined based on the driver's driving risk score determined by the driving risk index model, as follows: A driving risk score of less than 30 points is set as the first driving risk level; a driving risk score of greater than or equal to 30 points and less than 50 points is set as the second driving risk level; a driving risk score of greater than or equal to 50 points and less than 70 points is set as the third driving risk level; a driving risk score of greater than or equal to 70 points and less than 90 points is set as the fourth driving risk level; and a driving risk score greater than 90 points is set as the fifth driving risk level.

[0028] For example: by matching the real-time positioning data of trucks, locomotives, and construction machinery with a library of prohibited road section models, the system intelligently analyzes vehicle prohibited driving warning trends; by matching vehicle positioning data with an overspeeding algorithm model, the system intelligently analyzes vehicle speed, driver behavior, and driving habits; by matching vehicle positioning and driving time with a fatigue driving model algorithm, the system analyzes and issues warnings about the number and duration of driver fatigue driving; and by matching the nature, past violations, and frequency of truck, locomotive, and construction machinery operations with a suspected illegal operation algorithm model, the system analyzes and issues warnings about the illegal operation status and suspected illegal operation frequency of trucks, locomotives, and construction machinery. The above information is used to determine the driving risk score.

[0029] Step S104: Perform safety management on the driver based on the driver's driving risk level.

[0030] Specifically, drivers in the first driving risk level will be granted limited dispatching privileges; drivers in the second driving risk level will be equipped with a voice safety reminder system; drivers in the third driving risk level will be required to have their vehicles connected to a co-pilot assistance system; drivers in the fourth driving risk level will have dispatching privileges suspended and receive safety training; and drivers in the fifth driving risk level will have their driving qualification reconfirmed. Specifically, drivers in the green driving risk level (DRI < 30) will have priority dispatching privileges; drivers in the blue driving risk level (30 ≤ DRI < 50) will receive a voice safety reminder; drivers in the yellow driving risk level (50 ≤ DRI < 70) will be required to use the AI ​​co-pilot assistance system; drivers in the orange driving risk level (70 ≤ DRI < 90) will have dispatching privileges suspended and receive VR safety training; and drivers in the red driving risk level (DRI ≥ 90) will have their driving qualification reconfirmed.

[0031] Step S105: constructing a vehicle health index model based on the preprocessed data, determining a vehicle health level based on the vehicle health index model, and performing safety management on the vehicle based on the vehicle health level.

[0032] A vehicle health index model is constructed based on preprocessed data. It integrates 12 indicators such as OBD diagnostic data, maintenance records, and energy consumption characteristics to classify vehicles into the first health level, i.e. A (excellent), the second health level, i.e. B (good), and the third health level, i.e. C (pending maintenance).

[0033] For vehicles in the first health level, long-distance trunk transport tasks are prioritized. For vehicles in the second health level, short-distance cargo collection tasks are assigned. For vehicles in the third health level, smart maintenance work orders are issued to carry out maintenance.

[0034] Furthermore, based on the driver risk level and vehicle health level obtained in the above steps, a reinforcement learning algorithm is used to train a dispatching strategy. When a transport task is assigned, the optimal vehicle-route-driver combination is calculated in real time, reducing the idle rate by 23% and improving emergency response time to within 5 minutes. An emergency decision-making simulation system has been developed, generating response plans for 12 scenarios, such as rainstorms and traffic accidents, through digital twin simulation, improving emergency dispatch efficiency by 40%.

[0035] Step S106: Construct a driving risk prediction model based on the preprocessed data, predict driving risk behavior through the driving risk prediction model, and perform risk warning and disposal based on the driving risk behavior.

[0036] Specifically, a three-layer risk analysis architecture is constructed: Basic layer: Uses the random forest algorithm to build a driving risk prediction model, inputs 12 features such as sudden acceleration and lane departure, and outputs the risk level (AE level), with a prediction accuracy of 91.3%; Business layer: Develop a route heat analysis model based on historical waybill data and real-time traffic flow, calculate the probability of road congestion through graph neural networks, and support dynamic optimization of transportation routes; Strategic layer: Create a spatiotemporal propagation model for illegal behaviors, use LSTM networks to predict high-incidence periods and areas of illegal behaviors, and provide early warnings up to 30 minutes in advance.

[0037] At the same time, we established a closed-loop reinforcement learning system: "data collection - model training - decision output - effect evaluation." We automatically extract 10% of new data daily for incremental model training, and validate the effectiveness of algorithm iterations through A / B testing. We also developed an abnormal data annotation system, allowing operations personnel to flag false positives and false negatives, and reversely optimize feature engineering and model parameters, achieving a quarterly increase of 2-3 percentage points in risk identification accuracy.

[0038] We can timely intervene in various illegal and irregular behaviors during the operation of freight cars, locomotives and engineering machinery vehicles, realize real-time monitoring of vehicle operation dynamics, and implement risk warning and disposal. For example: TTS voice delivery, SMS push, notification of operation team for manual intervention, etc. Figure 2 .

[0039] In another embodiment of the present application, a management system for logistics transportation vehicles is provided. Figure 3 The system includes a data acquisition module, a data processing module, a first model construction module, a first security management module, a second model construction module and a third model construction module.

[0040] Specifically, the data acquisition module is used to collect real-time operational status data and driving behavior data from logistics vehicles. This operational status data includes vehicle location data, trajectory data, speed, comprehensive OBD diagnostic data, energy consumption data, and maintenance data. Driving behavior data includes video footage of the driver's driving process. This video data can be used to capture the driver's driving behavior and habits, such as the number and duration of instances of fatigue driving.

[0041] The data processing module is used to fuse and standardize the collected data from multiple sources and heterogeneous structures to generate preprocessed data. Specifically, the module uses big data, regional algorithms, risk identification, and digital twin processing mechanisms to classify, label, and process the acquired data. Active safety alarm data is associated with vehicle and enterprise information, and alarm data is aggregated and compiled. Tracking data is associated with vehicle information, and positioning data is aggregated and compiled, providing data support for the system.

[0042] The first model building module is used to build a driving risk index model based on the preprocessed data, and determine the driver's driving risk level based on the driving risk index model.

[0043] The first safety management module is used to perform safety management on the driver based on the driver's driving risk level.

[0044] The second model building module is used to build a vehicle health index model based on the preprocessed data, determine the vehicle health level based on the vehicle health index model, and perform safety management on the vehicle based on the vehicle health level.

[0045] The third model building module is used to build a driving risk prediction model based on the preprocessed data, predict driving risk behavior through the driving risk prediction model, and perform risk warning and disposal based on the driving risk behavior.

[0046] The management system for logistics and transportation vehicles also includes a visualization module, which consists of three sections. The left-screen intelligent analysis displays basic vehicle information, vehicle distribution, and vehicle risk statistics. Through intelligent data analysis, it can more comprehensively and accurately analyze the safety management status of trucks, locomotives, and construction vehicles, provide vehicle safety analysis services, and achieve precise vehicle management. The middle screen displays real-time monitoring images, supports real-time video carousels, and displays vehicle operation trajectories and risk data in real time. It accurately grasps the real-time data of key operating vehicles, promptly detects driver violations, and realizes real-time monitoring of the operation dynamics of trucks, locomotives, and construction vehicles. The right-screen intelligent analysis establishes data analysis models, deeply mines data features, and displays vehicle alarm data and 100-kilometer alarm rankings. This transforms vehicle alarm data into a basis for enterprise managers to guide decision-making, realizing the transformation of vehicle supervision to service and decision-making to data-driven, providing support for the supervision and analysis of trucks, locomotives, and construction vehicles.

[0047] Therefore, the technical solution of this application has built a logistics truck, railway locomotive and construction machinery management system covering the entire factory area, and unified planning and allocation of various materials. It integrates informationization, digitization, visualization and intelligence, standardizes logistics processes, reduces logistics costs, improves the company's logistics operation efficiency and management level, and provides timely and accurate data support for the company. It has strategic, overall and forward-looking characteristics, and effectively enhances the accident prevention capabilities in logistics transportation. At the same time, it can summarize the supervision experience of logistics trucks, railway locomotives and construction machinery vehicles, and summarize the working methods of vehicle risk prevention and control, hidden danger judgment, vehicle scheduling, emergency response, etc.

[0048] In addition to the above embodiments, the present invention may also have other implementation methods; any technical solutions formed by equivalent replacement or equivalent transformation fall within the protection scope required by the present invention.

Claims

1. A method for managing logistics transport vehicles, characterized by: include: Real-time collection of logistics vehicle operation status data and vehicle driving behavior data, Perform multi-source heterogeneous data fusion and standardization on the collected data to obtain pre-processed data; Building a driving risk index model based on the preprocessed data, and determining the driver's driving risk level based on the driving risk index model; Carry out safety management of drivers based on their driving risk levels.

2. The method for managing logistics transportation vehicles according to claim 1, characterized in that: The vehicle's operating status data includes vehicle positioning data, vehicle operating trajectory data, vehicle operating speed, comprehensive OBD diagnostic data, vehicle energy consumption data, and vehicle maintenance data; the vehicle driving behavior data includes driving process video data.

3. The method for managing logistics transportation vehicles according to claim 1, characterized in that: Determining the driver's driving risk level based on the driving risk index model includes: Determine the driver's driving risk score based on the driving risk index model; determining a driver's driving risk level based on the driver's driving risk score; Among them, the driving risk score is set to be less than 30 points as the first driving risk level; Set the driving risk score to be greater than or equal to 30 points and less than 50 points as the second driving risk level; The third driving risk level is set as a driving risk score greater than or equal to 50 points and less than 70 points; The fourth driving risk level is set as a driving risk score greater than or equal to 70 points and less than 90 points; A driving risk score greater than 90 is set as the fifth driving risk level.

4. The method for managing logistics transportation vehicles according to claim 3, characterized in that: The driver safety management based on the driver's driving risk level includes: Limited dispatching authority is granted to drivers in the first driving risk level; Add a voice safety reminder system for drivers in the second driving risk level; For drivers in the third driving risk level, vehicles used by them must be connected to the co-pilot assistance system; Drivers in the fourth driving risk level will be suspended from dispatching and given safety training; The driving qualification reaffirmation mechanism will be activated for drivers who are in the fifth driving risk level.

5. The method for managing logistics transportation vehicles according to claim 1, characterized in that: After the driver safety management is performed based on the driver's driving risk level, the method further includes: A vehicle health index model is constructed based on the preprocessed data, and a vehicle health level is determined based on the vehicle health index model, and safety management of the vehicle is performed based on the vehicle health level.

6. The method for managing logistics transportation vehicles according to claim 5, characterized in that: Determining the vehicle health level based on the vehicle health index model includes: determining a vehicle health score based on a vehicle health index model; determining a vehicle health rating based on the vehicle health score; The vehicle health level includes a first health level, a second health level and a third health level.

7. The method for managing logistics transportation vehicles according to claim 6, characterized in that: The vehicle safety management based on the vehicle health level includes: Vehicles of the first health level will be given priority in long-distance trunk transport tasks, vehicles of the second health level will be given priority in short-distance cargo collection tasks, and vehicles of the third health level will be maintained.

8. The method for managing logistics transportation vehicles according to claim 5, characterized in that: After constructing the vehicle health index model based on the preprocessed data, determining the vehicle health level based on the vehicle health index model, and performing safety management on the vehicle based on the vehicle health level, the method further includes: A driving risk prediction model is constructed based on the preprocessed data, driving risk behaviors are predicted through the driving risk prediction model, and risk warning and disposal are carried out based on driving risk behaviors.

9. A management system for logistics transportation vehicles, characterized by: include: Data acquisition module, used to collect real-time operation status data and driving behavior data of logistics vehicles; The data processing module is used to perform multi-source heterogeneous data fusion and standardization on the collected data to obtain pre-processed data; A first model building module is used to build a driving risk index model based on the preprocessed data, and determine the driver's driving risk level based on the driving risk index model; The first safety management module is used to perform safety management on the driver based on the driver's driving risk level.

10. The management system for logistics transportation vehicles according to claim 9, characterized in that: Also includes: a second model building module, configured to build a vehicle health index model based on the preprocessed data, determine a vehicle health grade based on the vehicle health index model, and perform safety management on the vehicle based on the vehicle health grade; The third model building module is used to build a driving risk prediction model based on the preprocessed data, predict driving risk behavior through the driving risk prediction model, and perform risk warning and disposal based on the driving risk behavior.

Images