Vehicle operation data management method and device

Abstract

The invention discloses a vehicle operation data management method and device, belongs to the technical field of data processing, and solves the technical problem that up-and-down linkage of multi-dimensional operation data cannot be realized, and the method comprises the steps: obtaining vehicle operation data of a logistics vehicle, the vehicle operation data comprising vehicle driving data, road data and environment data; analyzing the vehicle operation data to obtain an operation parameter value of the logistics vehicle; determining the parameter operation condition of the logistics vehicle according to the driving task of the logistics vehicle and the operation parameter value; the parameter operation condition comprises whether the parameter is abnormal or not and a parameter change trend; performing multi-parameter correlation analysis on the parameter operation condition to obtain operation state information of the logistics vehicle; and performing driving control on the logistics vehicle according to the running state information. The efficient management of the vehicle operation data can be realized.

Description

Technical Field

[0001] The present application relates to the field of data processing technology, and in particular to a vehicle operation data management method and device. Background Art

[0002] With the development of related technologies such as smart cars and intelligent networking, as well as the improvement of highway infrastructure, trunk logistics autonomous driving has become a new development trend as a mode of transportation in long-distance, large-scale logistics transportation. Trunk logistics autonomous driving vehicles refer to vehicles that are mainly used for trunk logistics transportation and can achieve autonomous driving functions to a certain extent. They are usually freight vehicles such as large trucks. It uses advanced sensors, controllers, algorithms and other technologies to enable the vehicle to automatically complete driving tasks, including acceleration, deceleration, steering, identification of traffic signals and road conditions, etc. In addition, whether the trunk logistics autonomous driving vehicle is completely unmanned when transporting logistics depends on factors such as the stage of technology development and application scenarios.

[0003] At present, in the data analysis and processing link, multi-dimensional operation data is usually analyzed independently and simply, and it is impossible to achieve the linkage of multi-dimensional operation data, and thus it is impossible to form a comprehensive operation status. Since the operating environment and conditions of the vehicle are constantly changing, if the vehicle operation status cannot be analyzed comprehensively and in depth, it is difficult to accurately judge the actual operation status of the vehicle and control the logistics vehicle more accurately. Summary of the invention

[0004] The embodiments of the present application provide a vehicle operation data management method and device, which are used to solve the problem of performing independent and simple analysis on multi-dimensional operation data and failing to achieve the upper and lower linkage of the multi-dimensional operation data.

[0005] The present application embodiment adopts the following technical solutions: On the one hand, an embodiment of the present application provides a vehicle operation data management method, which includes: acquiring vehicle operation data of a logistics vehicle, the vehicle operation data including vehicle driving data, road data and environmental data; analyzing the vehicle operation data to obtain operating parameter values ​​of the logistics vehicle; determining the parameter operating status of the logistics vehicle based on the driving task of the logistics vehicle and the operating parameter values; the parameter operating status includes whether the parameter is abnormal and the parameter change trend; performing multi-parameter correlation analysis on the parameter operating status to obtain operating status information of the logistics vehicle; and driving and controlling the logistics vehicle based on the operating status information.

[0006] In one example, the parameter operating status of the logistics vehicle is determined based on the driving mission of the logistics vehicle and the operating parameter value, specifically including: determining the multi-dimensional constraint threshold of the logistics vehicle based on the driving mission of the logistics vehicle; comparing the first operating parameter value with the preset parameter threshold to obtain the first parameter operating status of the logistics vehicle; the first parameter operating status is related to road parameters and environmental parameters; comparing the second operating parameter value with the multi-dimensional constraint threshold to determine the second parameter operating status of the logistics vehicle; the second parameter operating status is related to the vehicle's own parameters.

[0007] In one example, the multi-dimensional constraint threshold of the logistics vehicle is determined according to the driving task of the logistics vehicle, specifically including: obtaining the association weight between the first target parameter and the second target parameter from the dynamic threshold relationship map; the first target parameter causes the change of the second target parameter; in the dynamic threshold relationship map, the parameters with an associated relationship have their own reference values; calculating the deviation between the parameter value of the first target parameter and the corresponding reference value, and when the deviation is greater than a preset threshold, compensating the constraint threshold of the second target parameter according to the association weight; updating the driving task of the logistics vehicle according to the compensated constraint threshold, and extracting the multi-dimensional constraint threshold of the logistics vehicle from the updated driving task.

[0008] In one example, the constraint threshold of the second target parameter is compensated according to the associated weight, specifically including: obtaining the threshold adjustment amount of the second target parameter according to the product of the deviation and the associated weight; summing the threshold adjustment amount and the constraint threshold of the second target parameter to obtain the compensated constraint threshold of the second target parameter.

[0009] In one example, the multi-parameter association analysis of the parameter operating status is performed to obtain the operating status information of the logistics vehicle, specifically including: quantizing the parameter operating status to obtain the quantized state of the logistics vehicle; converting the quantized state into a vector by embedded coding to obtain the state vector of the logistics vehicle; concatenating multiple state vectors into a long vector; passing the long vector as input to a multi-parameter association model, so as to calculate the similarity between the long vector and each pre-stored state pattern vector by cosine similarity in the multi-parameter association model; determining the pre-stored state pattern vector whose similarity exceeds a similarity threshold as a target state pattern vector; and determining the operating status information of the target state pattern vector as the operating status information of the logistics vehicle.

[0010] In one example, the method further includes: constructing a plurality of associated parameters corresponding to each type of operating status information; performing vector conversion on the plurality of associated parameters to obtain a pre-stored state mode vector for each type of operating status information.

[0011] In one example, the driving control of the logistics vehicle according to the operating status information specifically includes: matching the first operating status information in the control rule set to obtain the control instruction of the first operating status information; the control instruction of the first operating status information is independent of updating the driving path; determining the alternative path of the logistics vehicle according to the driving task and map data; determining the access score of each path factor; the path factors include driving distance, driving time and potential congestion risk; updating the weights of the path factors according to the driving task; performing weighted summation of the access scores of each path factor according to the updated weight combination to obtain the access score of the alternative path; updating the driving path according to the alternative path with the highest access score to generate the control instruction of the second operating status information.

[0012] In one example, the method also includes: when the control instruction of the first operating status information includes adjusting the vehicle's driving speed when going straight, obtaining historical vehicle traffic data of the current driving section within the remaining time period of the historical day; the remaining time period of the historical day has a corresponding relationship with the remaining time period of the current day; performing speed statistics on the historical vehicle traffic data to generate vehicle speed distribution data; the speed distribution data refers to the distribution of the number of vehicles in different speed ranges; determining the conflict level between the speed range with the highest number of vehicles and the adjusted driving speed; when the conflict level is higher than a preset level, updating the adjusted driving speed according to the conflict level.

[0013] In one example, updating the adjusted driving speed according to the conflict level specifically includes: determining an adjustment amount of the adjusted driving speed according to a difference between the conflict level and a preset level, and a difference between the adjusted driving speed and an average value of a speed interval with the highest number of vehicles; and calculating the difference between the adjusted driving speed and the adjustment amount to obtain an updated adjusted driving speed.

[0014] On the other hand, an embodiment of the present application provides a vehicle operation data management device, comprising: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute a vehicle operation data management method described in any one of the above.

[0015] At least one of the above technical solutions adopted in the embodiments of the present application can achieve the following beneficial effects: By acquiring multiple vehicle operation data such as vehicle driving data, road data and environmental data of logistics vehicles, we can fully and comprehensively understand the actual operation of vehicles. These data cover the vehicle's own status, driving road conditions and external environmental factors, providing rich and accurate basic information for subsequent analysis and decision-making, avoiding the limitation of making judgments based on a single data.

[0016] Multi-parameter correlation analysis is performed on the parameter operation status to obtain the operation status information of the logistics vehicle. This multi-parameter correlation analysis can comprehensively consider the relationship between multiple parameters and discover potential risks that may be ignored by single parameter analysis, thereby improving the accuracy and reliability of early warnings and making the operation of logistics vehicles safer. In addition, combined with the multi-parameter correlation relationship, the actual driving status of logistics vehicles can be monitored more accurately.

[0017] Based on this, the operation data can be linked up and down to accurately monitor, analyze and manage the vehicle operation status, thereby achieving efficient management of vehicle operation data and improving logistics transportation efficiency and safety. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] In order to more clearly illustrate the technical solution of the present application, some embodiments of the present application will be described in detail below in conjunction with the accompanying drawings, in which: Figure 1 A schematic diagram of a vehicle operation data management system provided in an embodiment of the present application; Figure 2 A flow chart of a vehicle operation data management method provided in an embodiment of the present application; Figure 3 A schematic diagram of a historical on-board real-time video of a vehicle driving task provided in an embodiment of the present application; Figure 4 A schematic diagram of the structure of a vehicle operation data management device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0019] In order to make the purpose, technical solution and advantages of the present application clearer, the technical solution of the present application will be clearly and completely described below in conjunction with specific embodiments and corresponding drawings. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in the field without creative work are within the scope of protection of the present application.

[0020] Some embodiments of the present application are described in detail below with reference to the accompanying drawings.

[0021] Figure 1A schematic diagram of the framework of a vehicle operation data management system provided in an embodiment of the present application.

[0022] exist Figure 1 In the system, there are data layer, service layer, communication layer and presentation layer. The data layer includes Mysql (relational database management system) and Redis (data structure storage system). The service layer includes data analysis, abnormal event center and vehicle driving center. The communication layer includes Socket (to realize communication between networks), Netty (a high-performance network application framework based on Java), HTTP / HTTPS (Hypertext Transfer Protocol). The presentation layer includes Web (World Wide Web), GIS (geographic messaging system) and PC (personal computer).

[0023] The data layer is used to establish a data table structure related to vehicle operation data and to perform structured storage of vehicle operation data. Vehicle operation data may include vehicle driving data, road data, and environmental data. Vehicle driving data includes vehicle speed, fuel consumption, engine speed, engine temperature, vehicle tire pressure, vehicle position, driving trajectory, etc. Road data includes road type, road name, number of lanes, driving lanes, road images, etc. Environmental data includes weather conditions (e.g., sunny, rainy, snowy, foggy) and lighting conditions (e.g., daytime light intensity, nighttime street lighting conditions), etc.

[0024] The service layer is used to develop business data processing logic and data push function modules, responsible for the normalization and formatting of business data, and the implementation of data information push, such as pushing vehicle operation data to relevant management platforms or other related systems. In addition, the knowledge base data is standardized to facilitate accurate analysis and utilization of the data.

[0025] The communication layer is used to build a network communication environment to ensure stable data transmission between logistics vehicles and the data management center. It provides uplink and downlink data communication through Socket to realize data interaction between vehicles and the management data center. At the same time, it also ensures the stability and timeliness of data transmission and supports the transmission of multiple data formats (such as JSON).

[0026] The presentation layer is used to develop front-end interfaces, including vehicle operation screens, task management interfaces, statistical analysis interfaces, etc., to achieve user-friendly interactive design. For example, after single-point login and unified authentication, users can process business through a browser. Based on GIS maps, the vehicle operation screen is displayed to intuitively present the total number of vehicles, total mileage, fuel consumption, failure rate and other overall conditions. It can display the location of vehicles on the road, operation trajectory, operation indicators (vehicle speed, fuel consumption, etc.) in real time, and support vehicle video viewing.

[0027] Based on this, Figure 2A flow chart of a vehicle operation data management method provided in an embodiment of the present application. The process can be executed by a computing device in the corresponding field, and some input parameters or intermediate results in the process can be manually intervened to help improve accuracy. The method can also be applied to test the autonomous driving logistics vehicles in group operation.

[0028] The analysis method involved in the embodiments of the present application can be implemented by a terminal device or a server, and the present application does not impose any special restrictions on this. For the convenience of understanding and description, the following embodiments are described in detail by taking a server as an example.

[0029] It should be noted that the server may be a single device or a system consisting of multiple devices, that is, a distributed server, and this application does not make any specific limitation on this.

[0030] Figure 2 The process in includes the following steps: S201: Acquire vehicle operation data of a logistics vehicle, wherein the vehicle operation data includes vehicle driving data, road data, and environmental data.

[0031] It should be noted that when a logistics vehicle is traveling, a vehicle driving mission will be initiated. The vehicle driving mission information includes constraints such as destination, estimated arrival time, cargo type, speed limit (such as smooth driving for fragile goods), priority (such as emergency transportation), energy consumption limit (such as maximum fuel consumption), etc.

[0032] S202: Analyze the vehicle operation data to obtain the operation parameter value of the logistics vehicle.

[0033] Among them, the operating parameter dimensions include vehicle dimension, road dimension and environment dimension.

[0034] It should be noted that the vehicle dimensions include speed dimension (for example, average speed, maximum speed, speed standard deviation), mileage dimension (for example, mileage), driving time dimension (for example, driving time, parking time), trajectory dimension (for example, trajectory deviation), vehicle tire pressure dimension (for example, average tire pressure, tire pressure difference, tire pressure change rate), engine speed dimension (for example, average speed, maximum speed, speed change frequency), and vehicle energy consumption dimension (for example, average fuel consumption, energy consumption peak, energy consumption fluctuation coefficient).

[0035] Road dimensions include road condition dimensions (e.g., road accidents, construction zone obstacles, congestion index) and slope dimensions (e.g., average slope, maximum slope).

[0036] Environmental dimensions include road dimensions (e.g., humidity, rainfall, snowfall) and lighting dimensions (e.g., light intensity).

[0037] It should be noted that the process of analyzing vehicle operation data can be as follows: Regarding the speed dimension: the average speed is obtained by adding all the speed values ​​recorded in the vehicle operation data and dividing it by the total number of times recorded. The maximum speed can be obtained by comparing all the recorded speed values ​​and taking the maximum value. The speed standard deviation is calculated by the corresponding statistical formula to calculate the degree of dispersion of the speed value relative to the average value.

[0038] Regarding the mileage dimension: the mileage is calculated by calculating and accumulating the distances between adjacent location points in the vehicle operation data, and then adding the accumulated value to the mileage calculated last time to obtain the mileage of the logistics vehicle for this driving task.

[0039] For the driving time dimension: First, determine whether the vehicle is in driving or parking state. For example, when the vehicle speed is 0 and lasts for a certain period of time (such as more than 5 minutes), the vehicle is considered to be in parking state, otherwise it is in driving state. Then, accumulate the driving and parking time respectively.

[0040] Regarding the trajectory dimension: the vehicle's driving trajectory data is recorded by GPS, and the actual trajectory is compared with the preset planned trajectory. Dynamic time warping algorithms can be used to calculate the similarity or distance between the actual trajectory and the planned trajectory to measure the trajectory deviation.

[0041] Regarding the tire pressure dimension of the vehicle: Calculate the average of the recorded values ​​corresponding to the tire pressure values ​​of each tire to obtain the average tire pressure. Calculate the tire pressure difference between each tire to obtain the tire difference to evaluate the balance of tire pressure. Calculate the rate of change of tire pressure by comparing the tire pressure values ​​at adjacent time points.

[0042] Regarding the energy consumption dimension: the average energy consumption is obtained by dividing the total energy consumption (fuel or electricity) of the vehicle operation data by the corresponding mileage. The peak energy consumption is obtained by calculating the ratio of the standard deviation of the energy consumption data to the average value.

[0043] For the engine speed dimension: Calculate the average of the speed record values ​​in the vehicle operation data to obtain the average speed. Find the maximum value of the engine speed value in the speed record, that is, the maximum speed. Count the number of times the engine speed changes to obtain the speed change rate.

[0044] Regarding road conditions: image recognition technology can be used to analyze road images and combine with Amap data to identify features of the accident scene or construction area ahead. For example, when encountering road construction ahead, the laser radar and camera can identify construction warning signs and fences. The current congestion index can be obtained based on Amap data, or calculated using relevant congestion calculation models (such as models based on vehicle density, speed, and other factors) based on traffic flow data and road capacity.

[0045] In addition, when a logistics vehicle itself is involved in a traffic accident, on the one hand, a single-vehicle accident can be determined by automatically identifying the abnormal trajectory of the vehicle.

[0046] Among them, abnormal trajectory refers to the vehicle's driving trajectory that deviates significantly from the normal driving situation, such as sudden turns, running off the road, etc. Through the analysis of vehicle trajectories, if it is determined that the accident was caused by the abnormal behavior of a single vehicle itself, and there was no interaction with other vehicles, it can be determined as a single-vehicle accident.

[0047] On the other hand, the position information between vehicles is obtained and its change process is tracked to determine rear-end collision or side collision accidents.

[0048] For example, if a car gradually approaches the vehicle in front of it while driving, and the distance between them eventually becomes zero, and the subsequent position information shows that the two cars are closely connected, then a rear-end collision is likely to have occurred. If the side position information of the two cars overlaps or collides during driving, it may be determined to be a side collision accident.

[0049] On the other hand, image processing technology can be combined to automatically identify the cause of the accident. Image processing technology can identify and analyze various elements in the image, such as road signs, vehicle driving status, surrounding environment, etc. Through the comprehensive analysis of road images by the event neural network recognition model, the specific cause of the accident can be determined, such as whether it is due to speeding, illegal lane change, failure to pay attention to traffic signs, etc.

[0050] For the slope dimension: Use high-precision map data to obtain the terrain information of the road where the vehicle is traveling, including the slope data. By calculating the slope data of the vehicle operation data, the average slope and maximum slope are obtained.

[0051] For road dimensions: it is obtained based on the humidity, rainfall and snowfall of the vehicle's environment in the vehicle operation data. At the same time, the measurement results can also be supplemented and calibrated in combination with the real-time meteorological data of the meteorological department to obtain more accurate data.

[0052] For the light dimension: obtained based on the measured light intensity in the vehicle operation data.

[0053] S203: Determine the parameter operation status of the logistics vehicle according to the driving mission of the logistics vehicle and the operation parameter value; the parameter operation status includes whether the parameter is abnormal and the parameter change trend.

[0054] In some embodiments of the present application, it is considered that different logistics vehicles have different vehicle types and different cargo types, so the constrained driving conditions are also different. Therefore, the analysis is combined with the driving tasks of logistics vehicles. In addition, by establishing a dynamic constraint matching mechanism, an intelligent mapping of task requirements and real-time operating status is achieved, and the threshold is dynamically adjusted in combination with the influence of road parameters and environmental parameters, which improves the accuracy of abnormal recognition compared to the traditional fixed threshold detection method.

[0055] It should be noted that a logistics and transportation mapping relationship library for expressways will be established in advance, and the logistics and transportation mapping relationship library includes constraint thresholds of different operating parameters.

[0056] For example, when the cargo type is fragile goods, the speed standard deviation is less than 5km / h, the acceleration threshold is less than 0.3g, the temperature control energy consumption fluctuation coefficient of cold chain drugs is less than 10%, and when the priority is emergency transportation, the maximum speed allowed is 80km / h, the trajectory deviation tolerance is ±50 meters, and the driving overtime duration is no more than half an hour.

[0057] It should be noted that when setting the driving tasks of logistics vehicles, users will refer to the logistics transportation mapping relationship library.

[0058] Based on this, the process of determining the parameter operation status of logistics vehicles is as follows: Firstly, the multi-dimensional constraint thresholds of logistics vehicles are determined according to their driving tasks.

[0059] Then, the first operating parameter value is compared with the preset parameter threshold to obtain the first parameter operating status of the logistics vehicle, wherein the first parameter operating status is related to the road parameter and the environmental parameter.

[0060] For example, the road dimension detects abnormal conditions on the road through obstacles, road conditions, traffic congestion and other abnormal conditions.

[0061] In addition, the second operating parameter value is compared with the multi-dimensional constraint threshold to determine the second parameter operating status of the logistics vehicle, wherein the second parameter operating status is related to the vehicle's own parameters.

[0062] It should be noted that the parameter change trend of the logistics vehicle is obtained according to the sequence of parameter sampling time.

[0063] In some embodiments of the present application, the rule model developed based on domain knowledge and experience may be subjective and limited, and it is difficult to cover all possible situations. For example, it may not be accurate enough for certain special driving scenarios (such as judging the driving status on icy and snowy roads). Considering that during the driving of logistics vehicles on highways, road parameters and environmental parameters are usually in a dynamic change process, which have different degrees of impact on vehicle driving parameters. Therefore, when analyzing the vehicle operation data, it will be determined whether it is necessary to dynamically update the driving constraint threshold of the logistics vehicle in the current driving.

[0064] It should be noted that a dynamic threshold relationship graph will be pre-constructed, and the construction process may include: constructing a relationship graph consisting of a plurality of parameter nodes and associated edges between the plurality of parameter nodes.

[0065] It should be noted that the user pre-analyzes the association between various parameters in the operation process of logistics vehicles and finds parameter pairs where a change in one parameter will cause a change in another parameter. Then, through analysis of a large amount of logistics vehicle operation data, experiments, or industry experience, the baseline value of each parameter in the parameter pair is set, and the association weight of one parameter in the parameter pair causing another parameter change under the parameter baseline value is determined. Among them, the parameter baseline value of the same parameter in different parameter pairs may be the same or different.

[0066] It should be noted that in a simulated highway driving environment, developers can try different parameter association weights, give rewards or penalties based on the simulated driving results, and continuously optimize the association weights between parameters.

[0067] The determined parameter pairs and the associated weights between them are recorded and displayed in the form of a graph to form a dynamic threshold relationship graph. In the graph, the mutual influence relationship and the degree of influence between different parameters can be clearly seen.

[0068] Based on this, the process of determining the multi-dimensional constraint thresholds of logistics vehicles is as follows: From the dynamic threshold relationship map, the association weight between the first target parameter and the second target parameter is obtained, wherein the first target parameter causes a change in the second target parameter.

[0069] For example, the two parameters of snow accumulation and trajectory deviation, the thicker the snow accumulation, the higher the trajectory deviation will be. Or the two parameters of ambient temperature and energy consumption, when transporting cold chain products, the higher the ambient temperature, the higher the energy consumption will be. If the two parameters of ambient temperature and refrigeration temperature, the higher the ambient temperature, the lower the refrigeration temperature will be.

[0070] Then, the deviation between the parameter value of the first target parameter and the corresponding reference value is calculated, and when the deviation is greater than the preset threshold, the constraint threshold of the second target parameter is compensated according to the association weight. It should be noted that the association relationship includes positive correlation and negative correlation.

[0071] The compensation process can be as follows: First, the product of the deviation and the associated weight is calculated to obtain the threshold adjustment amount of the second target parameter. Then, the threshold adjustment amount is summed with the constraint threshold of the second target parameter to obtain the compensation constraint threshold of the second target parameter, and the constraint threshold of the second target parameter is adjusted.

[0072] It should be noted that the adjusted constraint threshold must not be higher than the parameter upper limit value.

[0073] For example, the correlation weight of ambient temperature to engine temperature is 0.8. When the ambient temperature rises by 5 degrees relative to the baseline value, the threshold of engine temperature needs to be adjusted up by 4 degrees. Therefore, the engine temperature threshold was originally 40 degrees, and is now adjusted to 44 degrees to reflect the impact of ambient temperature.

[0074] Then, the driving task of the logistics vehicle is updated according to the compensation constraint threshold, and the multi-dimensional constraint threshold of the logistics vehicle is extracted from the updated driving task.

[0075] S204: Perform multi-parameter correlation analysis on the parameter operating status to obtain the operating status information of the logistics vehicle.

[0076] It should be noted that operating status information refers to the comprehensive judgment result reflecting the real-time operating status of logistics vehicles obtained through multi-dimensional parameter correlation analysis. Its essence is to map multi-source heterogeneous dimensions such as vehicles, roads, and environment into decision-making semantic labels. For example, operating status information includes merging into the main road, driving on curves, turning, collision risk, loss of control warning, abnormal fuel consumption, battery degradation, path deviation, emergency transportation timeout warning, cargo damage risk (for example, unstable driving and bumpy risks of fragile goods), road construction detour, etc.

[0077] In some embodiments of the present application, in the process of operating status analysis, with the help of a multi-parameter association model, the operating status of a complex system that cannot be fully reflected by a single parameter can be more accurately characterized. It can comprehensively evaluate the changes in multiple parameters, avoid misjudgments or omissions that may occur when warning based on a single parameter, and thus improve the accuracy and reliability of warnings. By collecting, organizing and analyzing these parameters, a rich data foundation is provided for the generation of operating status information. The model can dig out the inherent correlations and potential laws between the various parameters, and analyze them in combination with the operating conditions of multiple parameters, thereby improving the accuracy of the analysis.

[0078] Based on this, firstly, a plurality of associated parameters corresponding to each type of running state information are constructed, and then the plurality of associated parameters are vector-converted to obtain a pre-stored state mode vector for each type of running state information.

[0079] It should be noted that the multiple associated parameters of the operating status information can be obtained by analyzing and summarizing a large amount of historical accident data, safe driving data and expert experience.

[0080] Based on this, the parameter operating status is quantified to obtain the quantized state of the logistics vehicle. Then, the quantized state is converted into a vector by embedded coding to obtain the state vector of the logistics vehicle. Then, multiple state vectors are concatenated into a long vector. Then, the long vector is passed as input to the multi-parameter association model to calculate the similarity between the long vector and each pre-stored state pattern vector by cosine similarity in the multi-parameter association model. Finally, the pre-stored state pattern vector whose similarity exceeds the similarity threshold is determined as the target state pattern vector, so that the operating state information of the target state pattern vector is determined as the operating state information of the logistics vehicle.

[0081] S205: Controlling driving of the logistics vehicle according to the operating status information.

[0082] In some embodiments of the present application, the operation status information includes first operation status information and second operation status information. For example, the first operation status information includes merging into the main road, driving on a curve, turning, loss of control warning, abnormal fuel consumption, etc. The second operation status information includes road construction detour, congestion detour and accident detour, etc. The driving control process is as follows: In some embodiments of the present application, the control process of the first operating state information is as follows: The first operation status information is matched in the control rule set to obtain a control instruction for the first operation status information.

[0083] It should be noted that the control instructions of the first running state information have nothing to do with the driving path of the updated driving task. The control instructions at this time are generally used to fine-tune the vehicle speed, driving distance, tire pressure, temperature control, etc. to ensure that the vehicle travels safely and efficiently on the current path and meets the transportation requirements of the goods.

[0084] For example, when a logistics vehicle is about to merge into the main road at the entrance ramp of a highway, the millimeter-wave radar and camera on the vehicle continuously monitor the speed and distance of surrounding vehicles. At this time, the control rule for merging into the main road can be: when a suitable safety gap is detected on the main road, a reasonable acceleration is calculated based on the vehicle's own position and target speed. The engine control unit receives the command, increases the amount of fuel injection, and accelerates the vehicle smoothly, merges smoothly into the main road traffic, and reaches the set driving speed.

[0085] During the steering process and driving, the vehicle's LiDAR scans the surrounding environment in real time and builds a high-precision map. When encountering a curve, the control rule for driving on the curve can be: calculate the appropriate steering angle based on the map data, the vehicle's current driving speed and the curvature of the curve. The power steering system receives the command and controls the steering of the wheels to allow the vehicle to pass the curve smoothly.

[0086] In some embodiments of the present application, considering that the control instruction needs to adjust the vehicle's driving speed when it is traveling straight (that is, not a special driving scenario, such as merging into the main road, driving on a sudden curve, etc.), it is usually under the premise that the logistics vehicle is not in a congested situation when it is currently driving. One is that the driving speed exceeds the speed requirement of the cargo type, and the driving speed needs to be lowered; the other is that the driving speed is relatively low and cannot meet the requirement of on-time delivery, and the driving speed needs to be increased.

[0087] However, it is still necessary to verify the driving speed conditions in combination with the current driving section to prevent the adjustment of the driving speed from being inconsistent with the actual driving conditions of the road, especially for control instructions to increase the driving speed, so as to analyze it in combination with the traffic rules of the section to generate the optimal control strategy in advance, which can improve safety and save energy. It is especially suitable for application scenarios where the adjusted vehicle speed may be too fast, and the current driving section will gradually enter congestion during the remaining time of the day.

[0088] It should be noted that the current driving section refers to the road area that the logistics vehicle is currently driving through, and the road area is set according to actual conditions.

[0089] For example, taking the physical range of the road as the dimension: it is a section of road with clear geographical boundaries and can be identified by a specific geographical location, such as the road between two adjacent intersections, the section between two mileage markers on a highway, etc.

[0090] For example, on a highway, a vehicle is in a specific mileage interval between two toll stations, and the road in this interval is the current driving section.

[0091] Defined by relative position: The road within a certain distance range from the vehicle. This range can be determined according to specific application scenarios and needs.

[0092] Based on this, the historical vehicle traffic data of the current driving section in the remaining time period of the historical day is obtained.

[0093] It should be noted that the remaining time period of the historical day corresponds to the remaining time period of the current day. For example, if it is after 4 pm on the current day, then the remaining time period of the historical day is also after 4 pm.

[0094] Then, the speed statistics of historical vehicle traffic data are performed to generate the speed distribution data of the vehicles. It should be noted that the speed distribution data refers to the distribution of the number of vehicles in different speed ranges.

[0095] Then, the conflict level between the speed interval with the highest number of vehicles and the adjusted driving speed is determined. The conflict level can be obtained by calculating the difference between the average value of the speed interval with the highest number of vehicles and the adjusted driving speed, and then matching the difference in the conflict level mapping table. It should be noted that the conflict level mapping table includes different difference intervals corresponding to each conflict level.

[0096] Then, when the conflict level is higher than a preset level, the adjusted driving speed is updated according to the conflict level.

[0097] The update process is as follows: First, the adjustment amount of the adjusted driving speed is determined according to the difference between the conflict level and the preset level, and the difference between the adjusted driving speed and the average value of the speed interval with the highest number of vehicles.

[0098] Then, the difference between the adjusted running speed and the adjustment amount is calculated to obtain an updated adjusted running speed.

[0099] For example, the conflict level is 1-6, and the default level is 4. Construct a linear adjustment function, the linear adjustment function is as follows:

[0100] in, refers to the updated adjusted driving speed, is the average value of the speed interval with the highest number of vehicles, To adjust the driving speed, k is the adjustment step size, and k is greater than 0 and less than 1.

[0101] It should be noted that, based on the analysis that the above control instructions need to adjust the vehicle's driving speed when going straight, when the current driving section gradually enters an application scenario of congestion during the remaining time period of the day, it is equivalent to adjusting the driving speed to a relatively lower level, so that the vehicle's driving speed has sufficient safety margin. The above driving speed adjustment ratio is relatively easier to adapt to the congestion that gradually forms over time.

[0102] When the conflict level does not exceed the preset level, it means that the adjustment of driving speed has little conflict with the historical speed distribution and no adjustment is required.

[0103] Among them, when the conflict level exceeds the preset level, the adjustment amount ( ) is proportional to the portion by which the conflict level exceeds the preset level, and the update amplitude of the adjusted driving speed is higher when the difference between the adjusted driving speed and the speed interval average is larger.

[0104] It should be noted that adjusting the step length plays a role in regulating the speed adjustment amplitude to avoid excessive speed adjustment.

[0105] In some embodiments of the present application, the control process of the second operating state information is as follows: When changing lanes in congestion, construction zones, or vehicle accidents, which path should be chosen? Because the first path is chosen by the user at the start, when correcting the path, there may be multiple paths. Which path should be chosen autonomously at this time? The best driving path should be chosen that can avoid congestion or accident sections and minimize the impact on the overall traffic flow while meeting the mission requirements.

[0106] For example, logistics vehicles with urgent transportation tasks may prefer to choose routes with slightly higher traffic flow but shorter travel time; while vehicles transporting ordinary goods may prefer routes with relatively stable traffic flow and lower congestion risks.

[0107] Based on this, the alternative paths of the logistics vehicles are determined according to the driving tasks and map data. Then, the pass score of each path factor is determined. Then, the weight of the path factor is updated according to the driving tasks. According to the updated weight combination, the pass score of each path factor is weighted and summed to obtain the pass score of the alternative path. Finally, the driving path is updated according to the alternative path with the highest pass score to generate the control instruction of the second operation state information.

[0108] It should be noted that path factors may include driving distance, driving time and potential congestion risk.

[0109] Among them, the driving distance and driving time can be calculated in combination with map data.

[0110] In addition, even if the traffic conditions on the highway are dynamically changing, different sections still have certain traffic rules. Therefore, when determining the traffic score of potential congestion risk, the traffic rules of the section are still considered while combining the current traffic conditions, thereby improving the prediction accuracy. Therefore, users will build a highway section congestion database based on historical big data, which includes the congestion levels of different sections at different times.

[0111] Based on this, when the driving time interval is a holiday, the congestion level of the alternative path during the holiday is obtained from the road congestion database, and the congestion level is converted into a traffic score in the score mapping relationship table.

[0112] It should be noted that when the travel time interval is a non-holiday, the congestion level of the alternative path during the non-holiday period is obtained.

[0113] In some embodiments of the present application, the weight of each factor is dynamically adjusted according to the driving mission requirements of the logistics vehicle (such as cargo type, urgency, estimated arrival time, etc.) to ensure that the selected route best meets the actual needs. For example, if the goods are transported for emergency supplies, the weight of the estimated driving time may be greatly increased; if the goods have high requirements for driving stability, the weight of the potential congestion risk may be increased.

[0114] Based on this, the process of updating the weights of path factors according to the driving task is as follows: The weight influence factor value of each path weight is extracted from the driving task, and the weight influence factor value is matched in the weight compensation mapping relationship table to obtain a compensation coefficient. The compensation coefficient is multiplied by the corresponding path weight to obtain a compensation weight of the corresponding path weight. The compensation coefficient is greater than 1.

[0115] It should be noted that although the embodiments of the present application are based on Figure 2 Steps S201 to S205 are described in sequence, but this does not mean that steps S201 to S205 must be performed in a strict order. Figure 2 The order shown in the figure is to introduce and explain step S201 to step S205 in sequence, in order to facilitate those skilled in the art to understand the technical solution of the embodiment of the present application. In other words, in the embodiment of the present application, the order between step S201 to step S205 can be appropriately adjusted according to actual needs.

[0116] pass Figure 2 The method realizes the linkage of operation data, monitors, analyzes and manages the vehicle operation status in real time, and thus realizes efficient management of vehicle operation data and improves logistics transportation efficiency and safety.

[0117] Specifically, by obtaining multiple vehicle operation data such as vehicle driving data, road data and environmental data of logistics vehicles, we can fully and comprehensively understand the actual operation of vehicles. These data cover the vehicle's own status, driving road conditions and external environmental factors, providing rich and accurate basic information for subsequent analysis and decision-making, avoiding the limitations of making judgments based on only a single data.

[0118] The acquired vehicle operation data is analyzed to obtain the operation parameter values ​​of the logistics vehicle. In this way, the complex raw data can be converted into parameters with clear meaning and operability, thereby more accurately reflecting the operation status of the vehicle and providing a quantitative basis for subsequent evaluation and decision-making.

[0119] According to the driving tasks and operating parameter values ​​of logistics vehicles, the parameter operating status of the vehicle is determined, including whether the parameters are abnormal and the parameter change trend. In this way, abnormal conditions that occur during vehicle operation can be discovered in a timely manner, such as a sudden abnormal decrease in speed, abnormal increase in fuel consumption, etc., and the trend of parameter changes can be predicted, measures can be taken in advance to deal with potential problems, and the safety and reliability of vehicle operation can be improved.

[0120] Perform multi-parameter correlation analysis on the parameter operation status to obtain the operation status information of the logistics vehicle. This multi-parameter correlation analysis can comprehensively consider the relationship between multiple parameters and discover potential risks that may be overlooked by single parameter analysis. For example, by combining road data and vehicle driving data, it is possible to analyze whether the performance of the vehicle is normal under specific road conditions, so as to issue operation warnings more accurately and improve the accuracy and effectiveness of warnings. In addition, combined with multi-parameter correlation relationships, the actual driving status of logistics vehicles can be monitored more accurately.

[0121] More intuitively, after the above management system is built, the system building phase is completed. After the system building phase, it also includes the data collection and data transmission phase, the data processing and analysis phase, and the system application and management phase.

[0122] For the data collection and data transmission stage: install the vehicle system, radar, meteorological monitoring, etc. on the logistics vehicle, and debug it to ensure the accuracy and stability of the vehicle operation data collection. Among them, the vehicle system can collect vehicle driving data at preset time intervals and upload it to the data management center through the communication layer. The radar monitors the surrounding information of the vehicle in real time and transmits the vehicle position, speed, lane and other data to the data management center. Meteorological monitoring can communicate with the meteorological data service platform through the Internet of Vehicles technology, and the camera of the autonomous driving vehicle can capture the environmental image around the vehicle. Through image recognition technology and deep learning algorithms, the features in the image are analyzed to judge the current weather conditions. When abnormal weather is detected, the warning data will be sent to the data management center in time.

[0123] For the data processing and analysis stage: the data service layer receives the vehicle operation data uploaded by the logistics vehicles, performs pre-processing operations such as data cleaning and format conversion, and stores the pre-processed vehicle operation data. Then the vehicle operation data is analyzed to determine whether the logistics vehicles have any abnormalities (for example, speeding, fuel consumption, driving trajectory deviation), and whether the roads have any abnormalities (for example, congestion, accidents).

[0124] For the system application and management stage: managers log in to the system through a browser, view the vehicle operation screen according to their permissions, and understand the overall operation and real-time status of the vehicle. In addition, manage vehicle driving tasks, including creating tasks, viewing task details, monitoring task execution, etc. In addition, use the data statistics and analysis module to generate reports and analysis results to provide a basis for decision-making. In addition, user management, role management, and basic vehicle information management are performed through the system management module to ensure system security and data accuracy.

[0125] Based on the above stages, the functional modules of the vehicle operation data management system may include a vehicle operation large screen module, a real-time operation status and abnormal event center module, a vehicle driving task management module, a data statistical analysis module, a system management module, and a data interaction and management method module.

[0126] Among them, the vehicle operation large-screen module includes overall situation preview, vehicle operation trajectory query, vehicle operation index display, and on-board video viewing.

[0127] The overall situation preview refers to the use of GIS map as the base map to display indicators such as the total number of vehicles, total mileage, average fuel consumption, failure rate, and travel tasks for the day. For example, the travel task for the day can be detailed information on the travel tasks of multiple vehicles in a marshaling test scenario.

[0128] Among them, logistics vehicles in transit are displayed in real time on the map in the form of icons, and their locations can be refreshed. At the same time, road condition information layers such as emergencies, abnormal weather, and road congestion are displayed.

[0129] Vehicle operation track query means that the historical operation track of a logistics vehicle can be queried, and the driving path can be restored in a timeline manner, including real-time location updates, vehicle start and stop status, etc. In addition, the track query display page can also display vehicle departure time, vehicle return time, total mileage within the time period, driving speed, track points, driving location, point time, ACC status and other information.

[0130] Vehicle operation index display refers to receiving uploaded vehicle operation data in real time, presenting it in the form of indicators and automatically refreshing it.

[0131] By clicking on the vehicle icon, you can view the real-time status of the vehicle (vehicle speed, fuel consumption, location, and real-time video on the vehicle). It should be noted that you can search for a logistics vehicle by entering the license plate number in the vehicle search box. In addition, the real-time video page on the vehicle displays information such as the captured video image, driving speed, vehicle type, mileage for the day, accumulated mileage, vehicle status, associated tasks, positioning time, longitude and latitude, etc.

[0132] Figure 3A schematic diagram of historical on-board real-time video of a vehicle driving mission provided in an embodiment of the present application.

[0133] exist Figure 3 In the process of performing vehicle driving tasks, logistics vehicles generate real-time on-board videos in multiple continuous time periods.

[0134] Among them, the real-time operation status and abnormal event center module includes vehicle system data upload, radar data upload and fusion, meteorological monitoring data upload, road abnormality information push, and vehicle operation information push.

[0135] Vehicle system data uploading refers to the sending of real-time vehicle driving data (position, speed, fuel consumption, mileage, parking status, etc.) to the data management system.

[0136] Radar data upload and fusion refers to the sending of vehicle information (location, license plate, speed, lane, steering angle, etc.) monitored by radar to the data management system. For example, the system generates a preliminary trajectory of the vehicle and matches it with the map data to determine the actual driving path of the vehicle. On the basis of trajectory matching, when the trajectory deviates, a trajectory correction algorithm is used to predict and correct the vehicle's driving trajectory using historical trajectory data and current observations. At the same time, during the correction process, the system fuses the radar monitoring data with the vehicle position data to further optimize the vehicle's driving trajectory and improve the accuracy and reliability of the trajectory.

[0137] Meteorological monitoring data uploading refers to sending abnormal weather warning data (heavy fog, heavy rain, heavy snow, etc.) to the data management system.

[0138] Road abnormality information push refers to pushing road abnormality information to the vehicle-mounted system of logistics vehicles.

[0139] Vehicle operation information push refers to pushing vehicle operation data to the front-end interface in real time.

[0140] Among them, the vehicle driving task management module includes task creation and task viewing.

[0141] Creating a task means automatically creating a task while the vehicle is driving, binding the onboard data, and recording the driving node data.

[0142] Task viewing means viewing task details through the task list, including vehicle driving trajectory, on-board video, real-time uploading of vehicle operation data, and viewing the operation status inside and outside the vehicle through the on-board video.

[0143] Among them, the data statistical analysis module includes vehicle abnormality report generation, driving task report generation, and driving task report generation.

[0144] Vehicle abnormality report generation refers to the generation of reports based on abnormal information reported by the vehicle system (for example, abnormal parking, mechanical failure, emergency braking, etc.).

[0145] Driving task report generation refers to generating statistical reports based on historical driving tasks. It supports multi-condition query, report generation and export, and can be counted according to different time dimensions.

[0146] Vehicle operation analysis refers to the statistics of the vehicle's average speed, fuel consumption, gear position, failure rate, accident-occurring sections, etc., to provide data support for intelligent driving strategies.

[0147] Among them, the system management module includes user management, role management, and vehicle basic information management.

[0148] User management refers to the unified management of system users, which can create, modify and delete users.

[0149] Role management refers to establishing different system roles and authorizing roles to system modules. Roles can be created, modified, and deleted.

[0150] Vehicle basic information management refers to maintaining basic vehicle information (license plate, vehicle status, brand, age, mileage, etc.).

[0151] Among them, the data interaction and management method module refers to the collection of vehicle operation data by logistics vehicles through vehicle-computer systems, radars, meteorological monitoring and other equipment.

[0152] The vehicle operation data is transmitted to the data service layer of the data management center through the communication layer, and is stored in the data storage layer after being standardized and formatted.

[0153] The data management system analyzes vehicle operation data, identifies whether the vehicle operation status is abnormal and whether the road is abnormal, and then controls the logistics vehicles.

[0154] It should be noted that abnormal situations will promptly push relevant information to the vehicle or management platform, and generate corresponding reports and analysis results for management personnel to review.

[0155] Managers can perform vehicle task management, user management, role management and other operations through the system presentation layer. Operation instructions are transmitted to the data service layer and data storage layer through the communication layer to perform corresponding data update or query operations.

[0156] Based on this, the data management system realizes the comprehensive collection, efficient transmission, accurate storage and intelligent analysis of vehicle operation data, and improves the level of informatization of logistics and transportation management.

[0157] Through real-time monitoring and abnormal event push, the safety and reliability of vehicle driving are improved and the risk of accidents is reduced.

[0158] The data statistical analysis function provides strong support for optimizing driving strategies, improving transportation efficiency and reducing costs.

[0159] The system has good compatibility and scalability, and can be integrated with other related systems (such as logistics management systems, traffic management systems, etc.) to adapt to the evolving needs of intelligent transportation.

[0160] Obtain vehicle operation data of trunk logistics autonomous driving vehicles on highways; vehicle operation data includes basic vehicle information, driving trajectory, operation status and abnormal events; When the weather monitoring system detects heavy rain or fog, or driving obstacles, it can automatically link to the vehicle's driving status, re-plan the driving route or adjust the driving speed.

[0161] For example, during the execution of a mission, the system can track and record the changes in the vehicle's operating status in real time, and conduct comparative analysis based on preset mission parameters (such as the scheduled speed, fuel consumption limit, etc.). When the vehicle's operating status deviates from the preset range, the system can automatically trigger an alarm and prompt the driver to make adjustments.

[0162] For example, when the vehicle finds that the road conditions are poor or encounters an emergency during driving, the system can automatically generate a new driving task based on the real-time driving trajectory.

[0163] The driving trajectory data can be associated with the historical operation data of the vehicle to form a complete driving history record. This data can not only be used for subsequent analysis and report generation, but also provide training data for machine learning algorithms to improve the system's ability to predict future driving trajectories.

[0164] Vehicle driving data: Real-time collection of dynamic parameters such as speed, acceleration, fuel consumption, engine temperature, tire pressure, and braking frequency through on-board sensors.

[0165] Road data: Integrate GPS positioning, high-precision maps, real-time traffic flow (such as congestion level), weather conditions (such as rain and snow), slope, curve radius and other static and dynamic environmental parameters.

[0166] Based on the same idea, some embodiments of the present application also provide devices and non-volatile computer storage media corresponding to the above methods.

[0167] Figure 4 A schematic diagram of the structure of a vehicle operation data management device provided in an embodiment of the present application includes: at least one processor; and, a memory communicatively connected to the at least one processor; wherein, The memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute any one of the vehicle operation data management methods described above.

[0168] Some embodiments of the present application provide a vehicle operation data management non-volatile computer storage medium storing computer executable instructions, wherein the computer executable instructions can execute any of the above-described vehicle operation data management methods.

[0169] Each embodiment in this application is described in a progressive manner, and the same or similar parts between the embodiments can be referred to each other, and each embodiment focuses on the differences from other embodiments. In particular, for the device and medium embodiments, since they are basically similar to the method embodiments, the description is relatively simple, and the relevant parts can be referred to the partial description of the method embodiments.

[0170] The devices and media provided in the embodiments of the present application correspond one-to-one to the methods. Therefore, the devices and media also have similar beneficial technical effects as the corresponding methods. Since the beneficial technical effects of the methods have been described in detail above, the beneficial technical effects of the devices and media will not be repeated here.

[0171] It will be appreciated by those skilled in the art that embodiments of the present invention may be provided as methods, systems, or computer program products. Therefore, the present invention may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Furthermore, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0172] The present invention is described with reference to flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0173] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0174] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0175] In a typical configuration, a computing device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.

[0176] Memory may include non-permanent storage in a computer-readable medium, in the form of random access memory (RAM) and / or non-volatile memory, such as read-only memory (ROM) or flash RAM. Memory is an example of a computer-readable medium.

[0177] Computer readable media include permanent and non-permanent, removable and non-removable media that can be implemented by any method or technology to store information. Information can be computer readable instructions, data structures, program modules or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technology, compact disk read-only memory (CD-ROM), digital versatile disk (DVD) or other optical storage, magnetic cassettes, magnetic tape magnetic disk storage or other magnetic storage devices or any other non-transmission media that can be used to store information that can be accessed by a computing device. As defined herein, computer readable media does not include temporary computer readable media (transitory media), such as modulated data signals and carrier waves.

[0178] It should also be noted that the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, commodity or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, commodity or device. In the absence of more restrictions, the elements defined by the sentence "comprises a ..." do not exclude the existence of other identical elements in the process, method, commodity or device including the elements.

[0179] The above is only an embodiment of the present application and is not intended to limit the present application. For those skilled in the art, the present application may have various changes and variations. Any modification, equivalent replacement, improvement, etc. made within the technical principle of the present application should all fall within the protection scope of the present application.

Claims

1. A vehicle operation data management method, characterized in that: The method comprises: Acquire vehicle operation data of logistics vehicles, wherein the vehicle operation data includes vehicle driving data, road data and environmental data; Analyze the vehicle operation data to obtain the operation parameter value of the logistics vehicle; Determine the parameter operation status of the logistics vehicle according to the driving task of the logistics vehicle and the operating parameter value; the parameter operation status includes whether the parameter is abnormal and the parameter change trend; Performing multi-parameter correlation analysis on the parameter operation status to obtain the operation status information of the logistics vehicle; The logistics vehicle is driven and controlled according to the operating status information.

2. The method according to claim 1, characterized in that Determining the parameter operation status of the logistics vehicle according to the driving task of the logistics vehicle and the operation parameter value specifically includes: Determining a multi-dimensional constraint threshold of the logistics vehicle according to the driving mission of the logistics vehicle; Compare the first operating parameter value with the preset parameter threshold to obtain the first parameter operating status of the logistics vehicle; the first parameter operating status is related to the road parameter and the environmental parameter; The second operating parameter value is compared with the multi-dimensional constraint threshold to determine the second parameter operating status of the logistics vehicle; the second parameter operating status is related to the vehicle's own parameters.

3. The method according to claim 2, characterized in that Determining the multi-dimensional constraint threshold of the logistics vehicle according to the driving task of the logistics vehicle specifically includes: From the dynamic threshold relationship map, the association weight between the first target parameter and the second target parameter is obtained; the first target parameter causes the change of the second target parameter; in the dynamic threshold relationship map, the parameters with the association relationship have their own reference values; Calculating a deviation between a parameter value of a first target parameter and a corresponding reference value, and when the deviation is greater than a preset threshold, compensating a constraint threshold of the second target parameter according to the association weight; The driving task of the logistics vehicle is updated according to the compensation constraint threshold, and the multi-dimensional constraint threshold of the logistics vehicle is extracted from the updated driving task.

4. The method according to claim 3, characterized in that The compensating the constraint threshold of the second target parameter according to the association weight specifically includes: Obtaining a threshold adjustment amount of the second target parameter according to a product of the deviation and the association weight; The threshold adjustment amount and the constraint threshold of the second target parameter are summed to obtain the compensation constraint threshold of the second target parameter.

5. The method according to claim 1, characterized in that The performing of multi-parameter correlation analysis on the parameter operation status to obtain the operation status information of the logistics vehicle specifically includes: Quantifying the parameter operating status to obtain the quantified state of the logistics vehicle; Converting the quantized state into a vector by means of embedded coding to obtain a state vector of the logistics vehicle; Concatenate multiple state vectors into one long vector; Passing the long vector as input to a multi-parameter association model to calculate the similarity between the long vector and each pre-stored state pattern vector in the multi-parameter association model by cosine similarity; Determine the pre-stored state pattern vector whose similarity exceeds the similarity threshold as the target state pattern vector; The operating state information of the target state pattern vector is determined as the operating state information of the logistics vehicle.

6. The method according to claim 5, characterized in that The method further comprises: Construct multiple associated parameters corresponding to each type of running status information; The multiple associated parameters are vector-converted to obtain a pre-stored state mode vector for each type of operating state information.

7. The method according to claim 1, characterized in that The driving control of the logistics vehicle according to the operating status information specifically includes: Matching the first running state information in the control rule set to obtain a control instruction for the first running state information; the control instruction for the first running state information is irrelevant to updating the driving path; Determine alternative routes for the logistics vehicle based on the driving mission and map data; Determine a traffic score for each path factor; the path factors include travel distance, travel time, and potential congestion risk; According to the driving task, weights of path factors are updated; According to the updated weight combination, the pass score of each path factor is weighted and summed to obtain the pass score of the alternative path; The driving path is updated according to the alternative path with the highest pass score to generate a control instruction for the second operating state information.

8. The method according to claim 7, characterized in that The method further comprises: When the control instruction of the first operation state information includes adjusting the driving speed of the vehicle when traveling straight, obtaining the historical vehicle traffic data of the current driving section within the remaining time period of the historical day; the remaining time period of the historical day has a corresponding relationship with the remaining time period of the current day; Perform speed statistics on historical vehicle traffic data to generate vehicle speed distribution data; the speed distribution data refers to the distribution of the number of vehicles in different speed ranges; Determine the conflict level between being in the speed zone with the highest number of vehicles and adjusting the driving speed; When the conflict level is higher than a preset level, the adjusted driving speed is updated according to the conflict level.

9. The method according to claim 8, characterized in that The updating of the adjusted driving speed according to the conflict level specifically includes: determining an adjustment amount of the adjusted driving speed according to a difference between the conflict level and a preset level and a difference between the adjusted driving speed and an average value of a speed interval with the highest number of vehicles; A difference between the adjusted travel speed and the adjustment amount is calculated to obtain an updated adjusted travel speed.

10. A vehicle operation data management device, characterized in that: include: at least one processor; as well as, a memory communicatively connected to the at least one processor; wherein, The memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute a vehicle operation data management method as described in any one of claims 1-9.

Images