A method and device for managing vehicle operation data

Abstract

The present application discloses a method and device for managing vehicle operation data, belonging to the technical field of data processing, and solving the technical problem that the up-and-down linkage of multi-dimensional operation data cannot be achieved. The method includes: obtaining the vehicle operation data of a logistics vehicle, where the vehicle operation data includes vehicle driving data, road data, and environmental data; analyzing the vehicle operation data to obtain the operation parameter values of the logistics vehicle; determining the parameter operation status of the logistics vehicle according to the driving task of the logistics vehicle and the operation parameter values; 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; and performing driving control on the logistics vehicle according to the operation status information. It can achieve efficient management of vehicle operation data.

Description

Technical Field

[0001] This application relates to the technical field of data processing, and particularly to a method and device for managing vehicle operation data. Background Art

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

[0003] Currently, in the data analysis and processing link, multi-dimensional operation data is usually analyzed independently and simply, and the up-and-down linkage of multi-dimensional operation data cannot be achieved, and thus a comprehensive operation state cannot be formed. Since the operating environment and conditions of the vehicle are constantly changing, it is difficult to accurately judge the true operating condition of the vehicle and control the logistics vehicle more accurately if the vehicle operating state cannot be analyzed comprehensively and deeply. Summary of the Invention

[0004] Embodiments of this application provide a method and device for managing vehicle operation data, which are used to solve the problem that multi-dimensional operation data is analyzed independently and simply and the up-and-down linkage of multi-dimensional operation data cannot be achieved.

[0005] Embodiments of this application adopt the following technical solutions:

[0006] On the one hand, embodiments of this application provide a method for managing vehicle operation data. The method includes: obtaining vehicle operation data of a logistics vehicle, where the vehicle operation data includes vehicle driving data, road data, and environmental data; analyzing the vehicle operation data to obtain operation parameter values of the logistics vehicle; determining the parameter operation status of the logistics vehicle according to the driving task of the logistics vehicle and the operation parameter values; 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 operation state information of the logistics vehicle; and performing driving control on the logistics vehicle according to the operation state information.

[0007] In one example, determining the parameter operating condition of the logistics vehicle according to the driving task and the operating parameter value of the logistics vehicle specifically includes: determining the multi-dimensional constraint threshold of the logistics vehicle according to the driving task of the logistics vehicle; comparing the first operating parameter value with the parameter preset threshold to obtain the first parameter operating condition of the logistics vehicle; the first parameter operating condition is related to the road parameter and the environmental parameter; comparing the second operating parameter value with the multi-dimensional constraint threshold to determine the second parameter operating condition of the logistics vehicle; the second parameter operating condition is related to the vehicle's own parameters.

[0008] In one example, determining the multi-dimensional constraint threshold of the logistics vehicle according to the driving task of the logistics vehicle specifically includes: obtaining the correlation weight between the first target parameter and the second target parameter from the dynamic threshold relationship graph; the first target parameter causes the change of the second target parameter; in the dynamic threshold relationship graph, the parameters with correlation relationships have their respective 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 the preset threshold, compensating the constraint threshold of the second target parameter according to the correlation 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.

[0009] In one example, compensating the constraint threshold of the second target parameter according to the correlation weight specifically includes: obtaining the threshold adjustment amount of the second target parameter according to the product of the deviation and the correlation 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.

[0010] In one example, performing multi-parameter correlation analysis on the parameter operating condition to obtain the operating state information of the logistics vehicle specifically includes: quantifying the parameter operating condition to obtain the quantified state of the logistics vehicle; converting the quantified state into a vector by means of embedding coding to obtain the state vector of the logistics vehicle; splicing multiple state vectors into a long vector; using the long vector as an input to be passed to a multi-parameter correlation model, and in the multi-parameter correlation model, calculating the similarity between the long vector and each pre-stored state pattern vector through cosine similarity; determining the pre-stored state pattern vector with a similarity exceeding the similarity threshold as the target state pattern vector; determining the operating state information of the target state pattern vector as the operating state information of the logistics vehicle.

[0011] In one example, the method further includes: constructing a plurality of associated parameters corresponding to each piece of operating state information; performing vector transformation on the plurality of associated parameters to obtain a pre-stored state mode vector for each piece of operating state information.

[0012] In one example, the driving control of the logistics vehicle according to the operating state information specifically includes: matching the first operating state information in a control rule set to obtain a control instruction for the first operating state information; the control instruction for the first operating state information has nothing to do with updating the driving route; determining an alternative route for the logistics vehicle according to the driving task and map data; determining the passing score for each route factor; the route factors include driving distance, driving time, and potential congestion risk; updating the weight of the route factor according to the driving task; performing weighted summation on the passing scores of each route factor according to the updated weight combination to obtain the passing score of the alternative route; updating the driving route according to the alternative route with the highest passing score to generate a control instruction for the second operating state information.

[0013] In one example, the method further includes: when the control instruction for the first operating state information includes adjusting the driving speed of the vehicle when going straight, obtaining the historical vehicle passing data of the current driving section in 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 passing data to generate vehicle speed distribution data; the speed distribution data refers to the vehicle number distribution of the vehicle in different speed intervals; determining the conflict level between the speed interval with the highest vehicle number and the adjusted driving speed; when the conflict level is higher than the preset level, updating the adjusted driving speed according to the conflict level.

[0014] In one example, the updating of the adjusted driving speed according to the conflict level specifically includes: determining the adjustment amount of the adjusted driving speed 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 vehicle number; obtaining the difference between the adjusted driving speed and the adjustment amount to obtain the updated adjusted driving speed.

[0015] On the other hand, an embodiment of the present application provides a vehicle operation data management device, including: 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 to enable the at least one processor to execute a vehicle operation data management method as described in any one of the above.

[0016] The above at least one technical solution adopted in the embodiment of the present application can achieve the following beneficial effects:

[0017] By obtaining vehicle operation data from multiple aspects such as the vehicle driving data, road data, and environmental data of logistics vehicles, it is possible to comprehensively and integrally understand the actual situation of vehicle operation. These data cover the vehicle's own state, driving road conditions, and external environmental factors, providing rich and accurate basic information for subsequent analysis and decision-making, and avoiding the limitations of making judgments based on only single data.

[0018] Perform multi-parameter correlation analysis on the parameter operation status to obtain the operation status information of logistics vehicles. This multi-parameter correlation analysis can comprehensively consider the mutual relationships among multiple parameters, discover potential risks that may be overlooked in single-parameter analysis, thereby improving the accuracy and reliability of early warning, and making the driving of logistics vehicles safer. In addition, by combining the multi-parameter correlation relationship, the actual driving status of logistics vehicles can be monitored more precisely.

[0019] Based on this, realize the up-and-down linkage of operation data, precisely monitor, analyze, and manage the vehicle operation status, and then realize the efficient management of vehicle operation data, improving the efficiency and safety of logistics transportation. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] In order to more clearly illustrate the technical solutions of the present application, the following will detail some embodiments of the present application in conjunction with the accompanying drawings. In the drawings:

[0021] Figure 1 is a framework schematic diagram of a vehicle operation data management system provided by an embodiment of the present application;

[0022] Figure 2 is a flowchart schematic diagram of a vehicle operation data management method provided by an embodiment of the present application;

[0023] Figure 3 is a schematic diagram of historical in-vehicle real-time video of a vehicle driving task provided by an embodiment of the present application;

[0024] Figure 4 is a structural schematic diagram of a vehicle operation data management device provided by an embodiment of the present application. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0025] To make the objectives, technical solutions, and advantages of the present application clearer, the following will clearly and completely describe the technical solutions of the present application in conjunction with specific embodiments and the corresponding accompanying drawings. Obviously, the described embodiments are only a part of the embodiments of the present application, rather than all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the scope of protection of the present application.

[0026] The following will refer to the accompanying drawings to elaborate in detail some embodiments of the present application.

[0027] Figure 1 It is a schematic framework diagram of a vehicle operation data management system provided for an embodiment of the present application.

[0028] In Figure 1 it, the system includes a data layer, a service layer, a communication layer, and a presentation layer. The data layer includes Mysql (relational database management system) and Redis (data structure storage system). The service layer includes data analysis, an exception event center, and a vehicle driving center. The communication layer includes Socket (to achieve communication between networks), Netty (a high-performance network application framework based on Java), and HTTP / HTTPS (hypertext transfer protocol). The presentation layer includes Web (World Wide Web), GIS (geographic information system), and PC (personal computer).

[0029] Among them, the data layer is used to establish the data table structure related to vehicle operation data and perform structured storage of vehicle operation data. Vehicle operation data can 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 lane, road image, etc. Environmental data includes weather conditions (such as sunny, rainy, snowy, foggy) and lighting conditions (such as daylight intensity during the day and street lamp lighting conditions at night), etc.

[0030] 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 realizing data information push. For example, pushing vehicle operation data to relevant management platforms or other associated systems. In addition, standardize the knowledge base data to facilitate the accurate analysis and utilization of data.

[0031] The communication layer is used to build a network communication environment to ensure stable data transmission between the logistics vehicle and the data management center. Provide up and down data communication through Socket to realize data interaction between the vehicle 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).

[0032] The presentation layer is used to develop the front-end interface, including the large vehicle operation screen, task management interface, statistical analysis interface, etc., to achieve a user-friendly interaction design. For example, after single sign-on and unified authentication, users can perform business processing through a browser. Based on the GIS map, the large vehicle operation screen is displayed, intuitively presenting the overall situation such as the total number of vehicles, total mileage, fuel consumption, and failure rate. It can real-time display the position, running track, and running indicators (such as vehicle speed, fuel consumption, etc.) of the vehicles on the way, and support the viewing of on-vehicle videos.

[0033] Based on this, Figure 2 It is a schematic flowchart of a vehicle operation data management method provided by an embodiment of the present application. This process can be executed by a computing device in the corresponding field, and some input parameters or intermediate results in the process allow manual intervention and adjustment to help improve accuracy. This method can also be applied to autonomous logistics vehicles running in a test formation.

[0034] The implementation of the analysis method involved in the embodiments of the present application can be a terminal device or a server, and the present application does not make special restrictions on this. For the convenience of understanding and description, the following embodiments are described in detail with the server as an example.

[0035] It should be noted that the server can be a single device or a system composed of multiple devices, that is, a distributed server, and the present application does not make specific limitations on this.

[0036] Figure 2 The process in

[0037] S201: Obtain the vehicle operation data of the logistics vehicle, where the vehicle operation data includes vehicle driving data, road data, and environmental data.

[0038] It should be noted that when the logistics vehicle travels, a vehicle driving task will be started, and the vehicle driving task information includes constraints such as destination, estimated arrival time, cargo type, speed limit (such as fragile items need to be driven smoothly), priority (such as emergency transportation), and energy consumption limit (such as maximum fuel consumption).

[0039] S202: Analyze the vehicle operation data to obtain the operation parameter values of the logistics vehicle.

[0040] Among them, the operation parameter dimensions include vehicle dimension, road dimension, and environmental dimension.

[0041] It should be noted that the vehicle dimensions include the speed dimension (such as average speed, maximum speed, speed standard deviation), mileage dimension (such as driving mileage), driving time dimension (such as driving time, parking time), trajectory dimension (such as trajectory deviation), vehicle tire pressure dimension (such as average tire pressure, tire pressure difference, tire pressure change rate), engine speed dimension (such as average speed, maximum speed, speed change frequency), and vehicle energy consumption dimension (such as average fuel consumption, energy consumption peak, energy consumption fluctuation coefficient).

[0042] The road dimensions include the road condition dimension (such as road accidents, construction area obstacles, congestion index) and the slope dimension (such as average slope, maximum slope).

[0043] The environmental dimensions include the road surface dimension (such as humidity, rainfall, snowfall) and the lighting dimension (such as lighting intensity).

[0044] It should be noted that the process of analyzing vehicle operation data can be as follows:

[0045] For the speed dimension: The average speed is obtained by adding all the speed values recorded in the vehicle operation data and then dividing by the total number of records. 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 measure the degree of dispersion of the speed values relative to the average value.

[0046] For the mileage dimension: The driving mileage is obtained by calculating the distance between adjacent position points in the vehicle operation data and accumulating them, and then adding the accumulated value to the previously calculated driving mileage to obtain the driving mileage of the logistics vehicle for the current driving task.

[0047] For the driving time dimension: First, it is determined whether the vehicle is in a 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 a parking state, otherwise it is in a driving state. Then, the driving and parking times are accumulated separately.

[0048] For the trajectory dimension: The driving trajectory data of the vehicle is recorded by GPS, and the actual trajectory is compared with the preset planned trajectory. Algorithms such as the dynamic time warping algorithm can be used to calculate the similarity or distance between the actual trajectory and the planned trajectory to measure the trajectory deviation.

[0049] For the vehicle tire pressure dimension: The average value of the recorded values corresponding to the tire pressure values of each tire is calculated to obtain the average tire pressure. The tire pressure difference between each tire is calculated to obtain the tire difference to evaluate the balance of the tire pressure. By comparing the tire pressure values at adjacent time points, the tire pressure change rate is calculated.

[0050] For the energy consumption dimension: Divide the total energy consumption (fuel volume or electricity) of the vehicle operation data by the driving mileage corresponding to this energy consumption to obtain the average energy consumption. Obtain the peak energy consumption according to the maximum value of the energy consumption recorded in the vehicle operation data. Calculate the ratio of the standard deviation to the average value of the energy consumption data to obtain the energy consumption fluctuation coefficient.

[0051] For the engine speed dimension: Calculate the average value of the recorded speed values in the vehicle operation data to obtain the average speed. Find the maximum value of the engine speed in the speed records, that is, the maximum speed. Count the number of changes in the engine speed to obtain the speed change rate.

[0052] For the road condition dimension: Road images can be analyzed through image recognition technology and combined with Amap data to identify the characteristics of the accident scene or construction area ahead. For example, when encountering road construction ahead, lidar and cameras can identify construction warning signs and fences. The current congestion index can be obtained according to Amap data, or calculated using relevant congestion calculation models (such as models based on factors such as vehicle density and speed) based on traffic flow data and road capacity.

[0053] In addition, when a traffic accident occurs to a logistics vehicle itself, on the one hand, a single-vehicle accident can be determined by automatically identifying the abnormal trajectory of the vehicle.

[0054] Among them, the abnormal trajectory refers to an obvious deviation of the vehicle driving trajectory compared with the normal driving situation, such as sudden turning, driving off the road, etc. Through the analysis of the vehicle trajectory, if it is determined that the accident is caused by the abnormal behavior of a single vehicle itself without interaction with other vehicles, it can be determined as a single-vehicle accident.

[0055] On the other hand, obtain the position information between vehicles and track its change process to determine rear-end accidents or side collision accidents.

[0056] For example, if a vehicle gradually approaches the vehicle ahead during driving, and finally the distance from the vehicle ahead becomes zero, and the subsequent position information shows that the two vehicles are closely connected, then a rear-end accident is likely to have occurred. If the side position information of the two vehicles overlaps or changes during driving, it may be determined as a side collision accident.

[0057] 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 states, surrounding environments, etc. Through the comprehensive analysis of road images by the event neural network recognition model, determine the specific cause of the accident, such as whether it is due to vehicle speeding, illegal lane change, failure to pay attention to traffic signs, etc.

[0058] For the slope dimension: Using high-precision map data, obtain the terrain information of the road on which the vehicle is traveling, including slope data. Calculate the average slope and the maximum slope by calculating the slope data of the vehicle operation data.

[0059] For the road surface dimension: Obtained from the humidity, rainfall, and snowfall of the environment where the vehicle is located in the vehicle operation data. At the same time, the real-time meteorological data of the meteorological department can also be combined to supplement and calibrate the measurement results to obtain more accurate data.

[0060] For the lighting dimension: Obtained from the measured lighting intensity in the vehicle operation data.

[0061] S203: Determine the parameter operation status of the logistics vehicle according to the driving task of the logistics vehicle and the operation parameter value; the parameter operation status includes whether the parameter is abnormal and the parameter change trend.

[0062] In some embodiments of the present application, considering that the vehicle types of different logistics vehicles are different and the cargo types are also different, the restricted driving conditions are also different. Therefore, analyze in combination with the driving task of the logistics vehicle. In addition, by establishing a dynamic constraint matching mechanism, an intelligent mapping between task requirements and real-time operation status is realized, and the threshold is dynamically adjusted in combination with the influence of road parameters and environmental parameters. Compared with the traditional fixed-threshold detection method, the accuracy of anomaly recognition is improved.

[0063] It should be noted that a logistics transportation mapping relationship library for highways will be established in advance. In the logistics transportation mapping relationship library, it includes the constraint thresholds of different operation parameters.

[0064] For example, when the cargo type is fragile, the speed standard deviation is less than 5 km / h, the acceleration threshold is less than 0.3 g, the temperature control energy consumption fluctuation coefficient of cold chain drugs is less than 10%, when the priority is urgent transportation, the maximum allowable speed is 80 km / h, the trajectory deviation tolerance is ±50 meters, and the duration of driving overtime is not higher than half an hour.

[0065] It should be noted that when the user sets the driving task of the logistics vehicle, the logistics transportation mapping relationship library will be referred to.

[0066] Based on this, the process of determining the parameter operation status of the logistics vehicle is as follows:

[0067] First, determine the multi-dimensional constraint thresholds of the logistics vehicle according to the driving task of the logistics vehicle.

[0068] Then, compare the first operation parameter value with the parameter preset threshold to obtain the first parameter operation status of the logistics vehicle. Among them, the first parameter operation status is related to road parameters and environmental parameters.

[0069] For example, the road dimension detects abnormal conditions existing in the road through abnormal conditions such as obstacles, road surface conditions, and traffic congestion.

[0070] In addition, the second operating parameter value is compared with the multi-dimensional constraint threshold to determine the operating condition of the second parameter of the logistics vehicle. Among them, the operating condition of the second parameter is related to the vehicle's own parameters.

[0071] It should be noted that according to the sequence of parameter sampling times, the parameter change trend of the logistics vehicle is obtained.

[0072] In some embodiments of the present application, the rule model formulated based on domain knowledge and experience may have subjectivity and limitations, and it is difficult to cover all possible situations. For example, for certain special driving scenarios (such as the driving state judgment on an icy road surface), it may not be accurate enough. Considering that during the driving process of a logistics vehicle on a highway, the road parameters and environmental parameters are usually in a dynamic change process, which have different degrees of influence on the vehicle driving parameters. Therefore, when analyzing the vehicle operation data, it will be judged whether it is necessary to dynamically update the driving constraint threshold of the logistics vehicle during the current driving.

[0073] It should be noted that a dynamic threshold relationship graph will be pre-constructed, and the construction process may include: constructing a relationship graph composed of multiple parameter nodes and associated edges between multiple parameter nodes.

[0074] It should be noted that the user pre-analyzes the associations between various parameters during the operation of the logistics vehicle, and finds parameter pairs where a change in one parameter causes a change in another parameter. Then, through the analysis of a large amount of logistics vehicle operation data, experiments, or industry experience, etc., the reference value of each parameter in the parameter pair is set, and the association weight of one parameter in the parameter pair causing a change in another parameter under the reference value of the parameter is determined. Among them, for the same parameter in different parameter pairs, the reference value of this parameter may be the same or may be different.

[0075] It should be noted that in the simulated highway driving environment, developers can try different parameter association weights, give rewards or punishments according to the simulated driving effects, and continuously optimize the association weights between parameters.

[0076] Among them, the determined parameter pairs and their association weights are recorded and displayed in the form of a graph to form a dynamic threshold relationship graph. In the graph, the mutual influence relationship between different parameters and the degree of influence can be clearly seen.

[0077] Based on this, the process of determining the multi-dimensional constraint threshold of the logistics vehicle is as follows:

[0078] From the dynamic threshold relationship graph, obtain the correlation weight between the first target parameter and the second target parameter. Among them, the change of the second target parameter is caused by the first target parameter.

[0079] For example, for the two parameters of snow accumulation amount and trajectory deviation degree, the thicker the snow accumulation, the relatively higher the trajectory deviation degree. Or for the two parameters of environmental temperature and energy consumption, when transporting cold-chain products, the higher the environmental temperature, the relatively higher the energy consumption. If it is the two parameters of environmental temperature and refrigeration temperature, the higher the environmental temperature, the relatively lower the refrigeration temperature.

[0080] Then, calculate the deviation between the parameter value of the first target parameter and the corresponding reference value. When the deviation is greater than the preset threshold, compensate the constraint threshold of the second target parameter according to the correlation weight. It should be noted that the correlation relationship includes positive correlation and negative correlation.

[0081] Among them, the compensation process can be as follows:

[0082] First, calculate the product of the deviation and the correlation weight to obtain the threshold adjustment amount of the second target parameter. Then, sum the threshold adjustment amount and the constraint threshold of the second target parameter to obtain the compensated constraint threshold of the second target parameter, and adjust the constraint threshold of the second target parameter.

[0083] It should be noted that the adjusted constraint threshold shall not be higher than the parameter upper limit value.

[0084] For example, the correlation weight of the environmental temperature on the engine temperature is 0.8. When the environmental temperature rises by 5 degrees relative to the reference value, the threshold of the engine temperature needs to be increased by 4 degrees. Therefore, the original threshold of the engine temperature is 40 degrees, and now it is adjusted to 44 degrees to reflect the influence of the environmental temperature.

[0085] Then, update the driving task of the logistics vehicle according to the compensated constraint threshold, and extract the multi-dimensional constraint threshold of the logistics vehicle from the updated driving task.

[0086] S204: Perform multi-parameter correlation analysis on the parameter operation status to obtain the operation status information of the logistics vehicle.

[0087] It should be noted that the operation status information refers to the comprehensive judgment result reflecting the real-time operation status of the logistics vehicle obtained through multi-dimensional parameter correlation analysis. Its essence is to map multi-source heterogeneous dimensions such as vehicles, roads, and environments into decision-making semantic labels. For example, the operation status information includes merging into the main road for driving, driving on a curve, steering, collision risk, out-of-control warning, abnormal fuel consumption, battery attenuation, path deviation, emergency transportation overtime warning, cargo damage risk (such as the unstable driving and bump risk of fragile items), road construction detour, etc.

[0088] 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.

[0089] 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.

[0090] 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.

[0091] 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.

[0092] S205: Controlling driving of the logistics vehicle according to the operating status information.

[0093] 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:

[0094] In some embodiments of the present application, the control process of the first operating state information is as follows:

[0095] The first operation status information is matched in the control rule set to obtain a control instruction for the first operation status information.

[0096] It should be noted that the control instruction of the first operating state information has nothing to do with updating the driving route of the driving task. At this time, the control instruction is generally used to fine-tune the vehicle speed, driving distance, tire pressure, temperature control, etc., to ensure the safe and efficient driving of the vehicle on the current route and meet the transportation requirements of the goods.

[0097] For example, when a logistics vehicle is about to merge into the main road at the highway entrance ramp, the millimeter-wave radar and camera on the vehicle continuously monitor the speeds and distances 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, calculate a reasonable acceleration based on the vehicle's own position and target speed. The engine control unit receives the instruction and increases the fuel injection volume to make the vehicle accelerate smoothly, merge into the main road traffic smoothly, and reach the set driving speed.

[0098] During the steering process, during the driving process, the vehicle's lidar scans the surrounding environment in real time to construct a high-precision map. When encountering a curve, the control rule for curve driving at this time can be: calculate a suitable steering angle based on the map data, the vehicle's current driving speed, and the curve curvature. The power steering system receives the instruction and controls the wheels to turn, so that the vehicle can pass through the curve smoothly.

[0099] In some embodiments of the present application, considering that when the control instruction needs to adjust the driving speed of the vehicle during straight driving (that is, not in special driving scenarios, such as merging into the main road, sudden curve driving, etc.), usually under the premise that the logistics vehicle is not in a congested situation during the current driving, one is that the driving speed exceeds the speed requirement of the cargo type and the driving speed needs to be lowered, and 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.

[0100] However, it is still necessary to verify in combination with the driving speed situation of the current driving section to prevent the adjusted driving speed from not conforming to the actual road driving situation, especially for the control instruction to increase the driving speed, so as to analyze in combination with the road traffic rules to pre-generate the optimal control strategy, which can improve safety and save energy, especially applicable to the application scenario where the adjusted vehicle driving speed may be too fast and the current driving section will gradually enter a congested situation during the remaining time of the day.

[0101] It should be noted that the current driving section refers to the section of road area that the logistics vehicle is currently driving through, and the road area is set according to the actual situation.

[0102] For example, taking the dimension of the physical scope of the road: it is a section of road with clear geographical boundaries, which can be identified by specific geographical locations, such as the road between two adjacent intersections, the section between two mileage markers on the highway, etc.

[0103] For example, on a highway, a vehicle is in a specific mileage range between two toll stations, and the road in this range is the current driving section.

[0104] Defined by relative position as the dimension: the road within a certain front and rear distance range centered on the vehicle. This range can be determined according to specific application scenarios and requirements.

[0105] Based on this, obtain the historical vehicle passing data of the current driving section in the remaining time period of the historical day.

[0106] It should be noted that the remaining time period of the historical day and the remaining time period of the current day are in a corresponding relationship. 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.

[0107] Then, conduct a speed statistics on the historical vehicle passing data to generate the speed distribution data of the vehicles. It should be noted that the speed distribution data refers to the vehicle quantity distribution within different speed ranges.

[0108] Then, determine the conflict level between the speed range with the highest vehicle quantity and the adjusted driving speed. Among them, the conflict level can be obtained by calculating the difference between the average value of the speed range with the highest vehicle quantity and the adjusted driving speed, and then matching this difference in the conflict level mapping relationship table. It should be noted that the conflict level mapping relationship table includes different difference intervals corresponding to each conflict level.

[0109] Then, when the conflict level is higher than the preset level, update the adjusted driving speed according to the conflict level.

[0110] Among them, the update process is as follows:

[0111] First, determine the adjustment amount of the adjusted driving speed 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 range with the highest vehicle quantity.

[0112] Then, calculate the difference between the adjusted driving speed and the adjustment amount to obtain the updated adjusted driving speed.

[0113] For example, the conflict level is 1 - 6, and the preset level is 4. Construct a linear adjustment function as follows:

[0114]

[0115] Among them, refers to the updated adjusted driving speed, is the average value of the speed range with the highest vehicle quantity, is the adjusted driving speed, and k is the adjustment step size, where k is greater than 0 and less than 1.

[0116] It should be noted that based on the analysis that the driving speed needs to be adjusted when the vehicle is going straight according to the above control instructions, when the current driving section gradually enters the application scenario of congestion in the remaining time period of the day, it is equivalent to relatively lowering the adjusted driving speed, so as to ensure that there is enough safety margin for the vehicle driving speed. The above driving speed adjustment ratio is relatively easier to adapt to the congestion situation gradually formed over time.

[0117] When the conflict level does not exceed the preset level, it indicates that the conflict between the adjusted driving speed and the historical speed distribution is small and no adjustment is required.

[0118] Among them, when the conflict level exceeds the preset level, the adjustment amount ( ) is proportional to the part by which the conflict level exceeds the preset level, and the greater the difference between the adjusted driving speed and the average value of the speed range, the higher the update amplitude of the adjusted driving speed.

[0119] It should be noted that the adjustment step plays a role in regulating the amplitude of speed adjustment to avoid excessive speed adjustment.

[0120] In some embodiments of the present application, the control process of the second operating state information is as follows:

[0121] When changing lanes due to congestion, construction areas or vehicle accidents, which path should be selected? Since the first path is selected by the user at the time of departure, there may be multiple paths when correcting the path. Which path should be autonomously selected at this time? Then, select the optimal driving path that can avoid congested or accident sections and minimize the impact on the overall traffic flow while meeting the task requirements of the vehicle.

[0122] For example, for logistics vehicles with urgent transportation tasks, they may be more inclined to choose a path with a slightly larger traffic flow but a shorter driving time; while for vehicles transporting ordinary goods, they may preferentially choose a path with relatively stable traffic flow and lower congestion risk.

[0123] Based on this, according to the driving task and map data, determine the alternative paths for the logistics vehicle. Then, determine the passing scores of each path factor. Then, according to the driving task, update the weights of the path factors. According to the updated weight combination, perform a weighted sum of the passing scores of each path factor to obtain the passing score of the alternative path. Finally, update the driving path according to the alternative path with the highest passing score to generate the control instruction for the second operating state information.

[0124] It should be noted that the path factors may include driving distance, driving time, and potential congestion risk.

[0125] Among them, the driving distance and driving time can be calculated in combination with map data.

[0126] In addition, even though the traffic conditions on the highway are dynamically changing, different sections still have certain traffic patterns. Therefore, when determining the traffic score of potential congestion risks, while considering the current traffic conditions, the traffic patterns of the sections are still taken into account to improve the prediction accuracy. Therefore, the user will construct a section congestion database for the highway based on historical big data, and the database includes the congestion levels of different sections at different times.

[0127] Based on this, when the driving time interval is a holiday, obtain the congestion level of the alternative route during the holiday from the section congestion database, and convert the congestion level into a traffic score in the score mapping relationship table.

[0128] It should be noted that when the driving time interval is not a holiday, obtain the congestion level of the alternative route during non-holidays.

[0129] In some embodiments of the present application, the weights of various factors are dynamically adjusted according to the driving task 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 emergency supplies are being transported, the weight of the estimated driving time may be significantly increased; if the cargo has high requirements for driving smoothness, the weight of the potential congestion risk may be increased.

[0130] Based on this, the process of updating the weights of the path factors according to the driving task is as follows:

[0131] Extract the weight influence factor values of each path weight from the driving task, match the weight influence factor values in the weight compensation mapping relationship table to obtain a compensation coefficient. Multiply the compensation coefficient by the corresponding path weight to obtain the compensated weight of the corresponding path weight. The compensation coefficient is greater than 1.

[0132] It should be noted that although the embodiments of the present application are described with reference to Figure 2 to introduce and illustrate steps S201 to S205 in sequence, this does not mean that steps S201 to S205 must be executed in a strict order. The reason why the embodiments of the present application introduce and illustrate steps S201 to S205 in the order shown in Figure 2 is to facilitate those skilled in the art to understand the technical solution of the embodiments of the present application. In other words, in the embodiments of the present application, the order between steps S201 to S205 can be appropriately adjusted according to actual needs.

[0133] Through Figure 2The method realizes the up-and-down linkage of operation data, monitors, analyzes, and manages the vehicle operation status in real time, thereby realizing the efficient management of vehicle operation data and improving the logistics transportation efficiency and safety.

[0134] Specifically, by obtaining various vehicle operation data such as the vehicle driving data, road data, and environmental data of logistics vehicles, the actual situation of vehicle operation can be comprehensively and integrally understood. 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, and avoiding the limitations of making judgments based on only single data.

[0135] Analyze the obtained vehicle operation data to obtain the operation parameter values of the logistics vehicle. In this way, complex original data can be transformed into parameters with clear meanings and operability, so as to more accurately reflect the vehicle operation status and provide a quantitative basis for subsequent evaluation and decision-making.

[0136] According to the driving tasks and operation parameter values of the logistics vehicle, determine the parameter operation status of the vehicle, including whether the parameters are abnormal and the parameter change trends. In this way, abnormal situations occurring during vehicle operation can be detected in a timely manner. For example, the speed suddenly decreases abnormally, the fuel consumption increases abnormally, etc. And the change trends of the parameters can be predicted, and measures can be taken in advance to deal with potential problems, improving the safety and reliability of vehicle operation.

[0137] Conduct 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 mutual relationships among multiple parameters and discover potential risks that may be ignored by single-parameter analysis. For example, by combining road data and vehicle driving data, it can be analyzed whether the vehicle's performance is normal under specific road conditions, so as to issue operation warnings more accurately and improve the accuracy and effectiveness of the warnings. In addition, by combining multi-parameter correlation relationships, the actual driving status of the logistics vehicle can be monitored more precisely.

[0138] More intuitively, after the above management system is built and the system building stage is completed, after the system building stage, it also includes a data collection and data transmission stage, a data processing and analysis stage, and a system application and management stage.

[0139] For the data collection and data transmission stages: Install vehicle-mounted systems, radars, meteorological monitors, etc. on logistics vehicles and conduct debugging to ensure the accuracy and stability of vehicle operation data collection. Among them, the vehicle-mounted 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 information around the vehicle in real time and transmits data such as the vehicle's position, speed, and lane to the data management center. Meteorological monitoring can communicate with the meteorological data service platform through vehicle networking technology, and the camera of the autonomous vehicle can capture the environmental images around the vehicle. Through image recognition technology and deep learning algorithms, the features in the images are analyzed to judge the current weather conditions. When abnormal weather is detected, warning data is sent to the data management center in a timely manner.

[0140] For the data processing and analysis stages: The data service layer receives the vehicle operation data uploaded by logistics vehicles, performs preprocessing operations such as data cleaning and format conversion, and stores the preprocessed vehicle operation data. Then, the vehicle operation data is analyzed to determine whether there are abnormalities in the logistics vehicles (such as speeding, fuel consumption, deviation of driving trajectory), and whether there are abnormalities on the road (such as congestion, accidents).

[0141] For the system application and management stages: Managers log in to the system through a browser, view the vehicle operation large screen according to their permissions, and understand the overall operation situation and real-time status of the vehicles. In addition, manage the vehicle driving tasks, including creating tasks, viewing task details, monitoring the task execution process, 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, through the system management module, perform user management, role management, and vehicle basic information management to ensure the security of the system and the accuracy of the data.

[0142] Based on the above stages, the functional modules of the vehicle operation data management system can 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 statistics and analysis module, a system management module, and a data interaction and management method module.

[0143] Among them, the vehicle operation large screen module includes an overall situation preview, a vehicle operation trajectory query, a vehicle operation index display, and an on-vehicle video view.

[0144] The overall situation preview refers to using a GIS map as the base map to display indicators such as the total number of vehicles, total mileage, average fuel consumption, failure rate, and daily travel tasks. For example, the daily travel tasks can be the detailed information of the travel tasks of multiple vehicles in the formation test scenario.

[0145] Among them, the in-transit logistics vehicles are displayed on the map in the form of icons in real time, the position can be refreshed, and at the same time, road condition information layers such as emergencies, abnormal weather, and road congestion are displayed.

[0146] Vehicle operation trajectory query means that the historical operation trajectory of a certain logistics vehicle can be queried, and the driving path can be restored in the form of a time axis, including real-time position updates, vehicle start and stop states, etc. In addition, on the trajectory query display page, information such as the vehicle's departure time, return time, total mileage within the time period, driving speed, trajectory points, driving position, point time, ACC status, etc. can also be displayed.

[0147] Vehicle operation index display means receiving the uploaded vehicle operation data in real time, presenting it in the form of an index, and automatically refreshing it.

[0148] By clicking on the vehicle icon, the real-time status of the vehicle (speed, fuel consumption, position, on-vehicle real-time video) can be viewed. It should be noted that a certain logistics vehicle can be queried by entering the license plate number in the vehicle search box. In addition, on the on-vehicle real-time video page, information such as the captured video image, driving speed, vehicle type, daily mileage, cumulative mileage, vehicle status, associated tasks, positioning time, longitude and latitude, etc. is displayed.

[0149] Figure 3 It is a schematic diagram of the historical on-vehicle real-time video of a vehicle driving task provided by an embodiment of the present application.

[0150] In Figure 3 During the process of a logistics vehicle performing a vehicle driving task, on-vehicle real-time videos in multiple consecutive time periods are generated.

[0151] 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 abnormal information push, and vehicle operation information push.

[0152] Vehicle system data upload means sending the real-time driving data of the vehicle (position, speed, fuel consumption, mileage, parking status, etc.) to the data management system.

[0153] Radar data upload and fusion means sending the vehicle information monitored by the radar (position, license plate, speed, lane, steering angle, etc.) 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 adopted, and historical trajectory data and current observation values are used to predict and correct the driving trajectory of the vehicle. At the same time, during the correction process, the system fuses the radar monitoring data with the vehicle position data to further optimize the driving trajectory of the vehicle and improve the accuracy and reliability of the trajectory.

[0154] Meteorological monitoring data upload means sending abnormal weather warning data (such as heavy fog, heavy rain, heavy snow, etc.) to the data management system.

[0155] The push of road anomaly information refers to pushing road anomaly information to the in-vehicle system of logistics vehicles.

[0156] The push of vehicle operation information refers to pushing vehicle operation data to the front-end interface in real time.

[0157] Among them, the vehicle driving task management module includes task creation and task viewing.

[0158] Task creation means automatically creating a task when the vehicle is driving, binding on-vehicle data, and recording driving node data.

[0159] Task viewing means viewing task details through the task list, including the vehicle driving trajectory, in-vehicle video, uploading vehicle operation data in real time, and viewing the running conditions inside and outside the vehicle through the in-vehicle video.

[0160] Among them, the data statistics and analysis module includes the generation of vehicle anomaly reports, the generation of driving task reports, and the generation of driving task reports.

[0161] The generation of vehicle anomaly reports means generating reports based on the anomaly information reported by the in-vehicle system (such as abnormal parking, mechanical failures, emergency braking, etc.).

[0162] The generation of driving task reports means generating statistical reports according to historical driving tasks, supporting multi-condition queries, report generation and export, and statistical analysis according to different time dimensions.

[0163] The analysis of vehicle operation conditions means statistically analyzing the average speed, fuel consumption, gear position, failure rate, accident-occurring sections, etc. of the vehicle, providing data support for intelligent driving strategies.

[0164] Among them, the system management module includes user management, role management, and vehicle basic information management.

[0165] User management means uniformly managing system users, and users can be created, modified, and deleted.

[0166] Role management means establishing different system roles, authorizing roles for system modules, and roles can be created, modified, and deleted.

[0167] Vehicle basic information management means maintaining vehicle basic information (license plate, vehicle status, brand, service life, mileage, etc.).

[0168] Among them, the data interaction and management method module means that logistics vehicles collect vehicle operation data through devices such as in-vehicle systems, radars, and meteorological monitors.

[0169] Vehicle operation data is transmitted to the data service layer of the data management center through the communication layer, and after being normalized and formatted, it is stored in the data storage layer.

[0170] The data management system analyzes the vehicle operation data to identify whether the vehicle operation status is abnormal and whether the road is abnormal, and then controls the logistics vehicles.

[0171] It should be noted that in case of abnormal situations, relevant information is pushed to the vehicle or the management platform in a timely manner, and corresponding reports and analysis results are generated for the management personnel to view.

[0172] The management personnel can perform operations such as vehicle task management, user management, and role management through the system presentation layer, and the operation instructions are transmitted through the communication layer to the data service layer and the data storage layer to execute corresponding data update or query operations.

[0173] Based on this, the data management system realizes the comprehensive collection, efficient transmission, accurate storage, and intelligent analysis of vehicle operation data, improving the informatization level of logistics transportation management.

[0174] Through real-time monitoring and abnormal event pushing, the safety and reliability of vehicle driving are improved, and the accident risk is reduced.

[0175] The data statistical analysis function provides strong support for optimizing driving strategies, improving transportation efficiency, and reducing costs.

[0176] The system has good compatibility and scalability, and can be integrated with other relevant systems (such as logistics management systems, traffic management systems, etc.) to meet the ever-developing intelligent transportation needs.

[0177] Obtain the vehicle operation data of trunk line logistics autonomous vehicles on highways; the vehicle operation data includes vehicle basic information, driving trajectories, operation status, and abnormal events;

[0178] When the meteorological monitoring system detects heavy rain or foggy weather, or driving obstacles, it can be automatically associated with the vehicle's driving status to re-plan the driving route or adjust the driving speed.

[0179] For example, during the task execution, the system can real-time track and record the changes in the vehicle's operation status, and conduct comparative analysis based on preset task parameters (such as the preset vehicle speed, fuel consumption limit, etc.). When the vehicle's operation status deviates from the preset range, the system can automatically trigger an alarm and prompt the driver to make adjustments.

[0180] For example, when the vehicle finds poor road conditions or encounters emergencies during driving, based on the real-time driving trajectory, the system can automatically generate a new driving task.

[0181] The driving trajectory data can be associated with the vehicle's historical operation data to form a complete driving history record. These 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 prediction ability for future driving trajectories.

[0182] Vehicle driving data: Dynamical parameters such as speed, acceleration, fuel consumption, engine temperature, tire pressure, braking frequency, etc. are collected in real time by in-vehicle sensors.

[0183] Road data: Static and dynamic environmental parameters such as GPS positioning, high-precision maps, real-time traffic flow (such as congestion level), weather conditions (such as rain and snow), slope, curve radius, etc. are integrated.

[0184] Based on the same idea, some embodiments of the present application also provide devices and non-volatile computer storage media corresponding to the above method.

[0185] Figure 4 The structure diagram of a vehicle operation data management device provided by an embodiment of the present application includes:

[0186] At least one processor; and,

[0187] A memory communicatively connected to the at least one processor; wherein,

[0188] 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.

[0189] A non-volatile computer storage medium for vehicle operation data management provided by some embodiments of the present application stores computer-executable instructions, and the computer-executable instructions can execute a vehicle operation data management method described in any one of the above.

[0190] Each embodiment in the present application is described in a progressive manner. The same or similar parts among the embodiments can be referred to each other, and the differences between each embodiment and other embodiments are emphasized. 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 refer to the partial description of the method embodiments.

[0191] The devices and media provided by the embodiments of the present application correspond one-to-one with the methods. Therefore, the devices and media also have beneficial technical effects similar to 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 are not elaborated here.

[0192] Those skilled in the art will understand that the embodiments of the present invention can be provided as a method, a system, or a computer program product. Therefore, the present invention can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Moreover, the present invention can take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk memory, CD-ROM, optical memory, etc.) that contain computer-usable program code.

[0193] The present invention is described with reference to the flowcharts and / or block diagrams of methods, apparatuses (systems), and computer program products according to the embodiments of the present invention. It should be understood that each flow and / or block in the flowchart and / or block diagram, and the combination of flows and / or blocks in the flowchart and / or block diagram, can be realized by computer program instructions. These computer program instructions can be provided to the processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing devices to generate a machine, such that the instructions executed by the processor of the computer or other programmable data processing devices generate means for implementing the functions specified in Figure 1 one flow or multiple flows and / or blocks Figure 1 one block or multiple blocks.

[0194] These computer program instructions can also be stored in a computer-readable memory that can direct a computer or other programmable data processing device to work in a specific manner, such that the instructions stored in the computer-readable memory generate a manufactured article including instruction means that implement the functions specified in Figure 1 one flow or multiple flows and / or blocks Figure 1 one block or multiple blocks.

[0195] These computer program instructions can also be loaded onto a computer or other programmable data processing device, such that a series of operation steps are executed on the computer or other programmable device to generate a computer-implemented process, and thus the instructions executed on the computer or other programmable device provide steps for implementing the functions specified in Figure 1 one flow or multiple flows and / or blocks Figure 1 one block or multiple blocks.

[0196] In a typical configuration, a computing device includes one or more processors (CPUs), an input / output interface, a network interface, and memory.

[0197] The memory may include non-permanent memory in the form of computer-readable media, random access memory (RAM), and / or non-volatile memory, such as read-only memory (ROM) or flash RAM. The memory is an example of a computer-readable medium.

[0198] A computer-readable medium includes both permanent and non-permanent, removable and non-removable media and can implement information storage by any method or technology. The 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 technologies, compact disc read-only memory (CD-ROM), digital versatile disc (DVD) or other optical storage, magnetic cassette tapes, magnetic tape magnetic disk storage or other magnetic storage devices, or any other non-transitory medium that can be used to store information that can be accessed by a computing device. As defined herein, a computer-readable medium does not include transitory computer-readable media, such as modulated data signals and carrier waves.

[0199] It should also be noted that the term "comprising", "including" or any other variation thereof is intended to cover non-exclusive inclusion, such that a process, method, article or apparatus comprising a series of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such process, method, article or apparatus. Without further limitation, an element defined by the statement "comprising an..." does not exclude the presence of additional identical elements in the process, method, article or apparatus comprising the element.

[0200] The above description is only for the embodiments of the present application and is not intended to limit the present application. For those skilled in the art, various changes and modifications can be made to the present application. Any modification, equivalent replacement, improvement, etc. made within the technical principles of the present application shall fall within the protection scope of the present application.

Claims

1. A vehicle operation data management method, characterized in that, The method includes: Obtaining the vehicle operation data of a logistics vehicle, where the vehicle operation data includes vehicle driving data, road data, and environmental data; Analyzing the vehicle operation data to obtain the operation parameter values of the logistics vehicle; Determining the parameter operation status of the logistics vehicle according to the driving task of the logistics vehicle and the operation parameter values; 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; Performing driving control on the logistics vehicle according to the operation status information; The performing multi-parameter correlation analysis on the parameter operation status to obtain the operation status information of the logistics vehicle specifically includes: Quantifying the parameter operation status to obtain the quantified status of the logistics vehicle; Converting the quantified status into a vector by means of embedded coding to obtain the status vector of the logistics vehicle; Concatenating multiple status vectors into a long vector; Using the long vector as an input to be passed to a multi-parameter correlation model, and in the multi-parameter correlation model, calculating the similarity between the long vector and each pre-stored status mode vector through cosine similarity; Determining the pre-stored status mode vectors with similarity exceeding the similarity threshold as target status mode vectors; Determining the operation status information of the target status mode vector as the operation status information of the logistics vehicle.

2. The method according to claim 1, wherein The determining the parameter operation status of the logistics vehicle according to the driving task of the logistics vehicle and the operation parameter values specifically includes: Determining the multi-dimensional constraint thresholds of the logistics vehicle according to the driving task of the logistics vehicle; Comparing the first operation parameter value with the parameter preset threshold to obtain the first parameter operation status of the logistics vehicle; the first parameter operation status is related to road parameters and environmental parameters; Comparing the second operation parameter value with the multi-dimensional constraint thresholds to determine the second parameter operation status of the logistics vehicle; the second parameter operation status is related to the vehicle's own parameters.

3. The method according to claim 2, wherein The determining the multi-dimensional constraint thresholds of the logistics vehicle according to the driving task of the logistics vehicle specifically includes: Obtaining the correlation weight between a first target parameter and a second target parameter from a dynamic threshold relationship graph; the first target parameter causes a change in the second target parameter; in the dynamic threshold relationship graph, there are respective reference values between parameters with a correlation relationship; Calculating the deviation between the parameter value of the first target parameter and the corresponding reference value, and when the deviation is greater than the preset threshold, compensating the constraint threshold of the second target parameter according to the correlation weight; Updating the driving task of the logistics vehicle according to the compensated constraint threshold, and extracting the multi-dimensional constraint thresholds of the logistics vehicle from the updated driving task.

4. The method according to claim 3, wherein The compensating the constraint threshold of the second target parameter according to the correlation weight specifically includes: Obtaining the threshold adjustment amount of the second target parameter according to the product of the deviation and the correlation weight; Sum the threshold adjustment amount and the constraint threshold of the second target parameter to obtain the compensation constraint threshold of the second target parameter.

5. The method according to claim 1, characterized in that, The method further includes: Construct multiple associated parameters corresponding to each type of operating state information; Perform vector conversion on the multiple associated parameters to obtain a pre-stored state mode vector for each type of operating state information.

6. The method according to claim 1, wherein The driving control of the logistics vehicle according to the operating state information specifically includes: Match the first operating state information in the control rule set to obtain a control instruction for the first operating state information; the control instruction for the first operating state information has nothing to do with updating the driving route; Determine an alternative route for the logistics vehicle according to the driving task and map data; Determine the passing score for each route factor; the route factors include driving distance, driving time, and potential congestion risk; Update the weight of the route factor according to the driving task; Perform weighted summation on the passing scores of each route factor according to the updated weight combination to obtain the passing score of the alternative route; Update the driving route according to the alternative route with the highest passing score to generate a control instruction for the second operating state information.

7. The method according to claim 6, wherein The method further includes: When the control instruction for the first operating state information includes adjusting the driving speed of the vehicle when going straight, obtain the historical vehicle passing data of the current driving section in 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 the historical vehicle passing data to generate speed distribution data of the vehicle; the speed distribution data refers to the vehicle quantity distribution of the vehicle in different speed intervals; Determine the conflict level between the speed interval with the highest vehicle quantity and the adjusted driving speed; When the conflict level is higher than the preset level, update the adjusted driving speed according to the conflict level.

8. The method according to claim 7, wherein The updating of the adjusted driving speed according to the conflict level specifically includes: Determine the adjustment amount of the adjusted driving speed 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 vehicle quantity; Obtain the difference between the adjusted driving speed and the adjustment amount to obtain the updated adjusted driving speed.

9. A vehicle operation data management device, characterized in that, Includes: 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 according to any one of claims 1-8 above.

Images