Driving behavior analysis method and vehicle networking server

Abstract

The invention provides a driving behavior analysis method and an Internet of Vehicles server. The method comprises the following steps: receiving vehicle driving data of a target vehicle in a preset historical time period uploaded by user equipment; performing feature extraction on the vehicle driving data to obtain a plurality of driving feature data; classifying the plurality of driving feature data to obtain driving feature data corresponding to a plurality of dimensions; according to the driving characteristic data corresponding to each dimension, performing driving behavior evaluation on the target vehicle in each dimension to obtain a driving behavior evaluation parameter of the target vehicle in each dimension; and sending target driving suggestion information to the user equipment according to the driving behavior evaluation parameters of the multiple dimensions. Therefore, statistics is performed on the driving characteristic data corresponding to each dimension, the driving behavior evaluation parameters of each dimension are obtained, and the target driving suggestion information is generated, so that more accurate and more reasonable driving behavior evaluation can be realized, and the actual performance of each driver is effectively reflected.

Description

Technical Field

[0001] The present invention relates to the field of vehicle technology, and in particular to a driving behavior analysis method and a vehicle networking server. Background Art

[0002] With the rapid development of science and technology, the performance of vehicles is getting better and better, and the main factor affecting driving safety lies in the driver of the vehicle. The driver's standardized driving behavior can greatly reduce the occurrence of traffic accidents. How to regulate the driver's driving behavior is an issue that the industry has always been concerned about.

[0003] In the prior art, the driver's behavior evaluation method is relatively simple and lacks a refined evaluation of driving behavior. Therefore, a more accurate driving behavior analysis method is urgently needed. Summary of the invention

[0004] The purpose of the present invention is to address the deficiencies in the above-mentioned prior art and provide a driving behavior analysis method and a vehicle networking server to solve the problems in the prior art such as the inability to accurately analyze driving behavior.

[0005] To achieve the above purpose, the technical solution adopted in the embodiment of the present application is as follows: In a first aspect, an embodiment of the present application provides a driving behavior analysis method, the method comprising: Receiving vehicle driving data of a target vehicle in a preset historical time period uploaded by a user device; Extracting features from the vehicle driving data to obtain a plurality of driving feature data; Classifying the plurality of driving characteristic data to obtain driving characteristic data corresponding to a plurality of dimensions; According to the driving characteristic data corresponding to each dimension, the driving behavior of the target vehicle is evaluated in each dimension to obtain the driving behavior evaluation parameters of the target vehicle in each dimension; According to the driving behavior evaluation parameters in the multiple dimensions, target driving suggestion information is sent to the user equipment.

[0006] Optionally, the plurality of driving characteristic data include: motion characteristic data, driving behavior characteristic data, interval characteristic data, drive motor characteristic data, and alarm characteristic data; The feature extraction of the vehicle driving data is performed to obtain a plurality of driving feature data, including: Performing a first feature extraction on the vehicle driving data to obtain the motion feature data; Performing a second feature extraction on the vehicle driving data to obtain the driving behavior feature data; Performing a third feature extraction on the vehicle driving data to obtain the interval feature data; A fourth feature extraction is performed on the vehicle driving data to obtain the drive motor feature data and the alarm feature data.

[0007] Optionally, the motion characteristic data includes: speed characteristic data, acceleration characteristic data, and deceleration characteristic data; The first feature extraction is performed on the vehicle driving data to obtain the motion feature data, including: Extracting speed characteristics according to the vehicle driving data to obtain vehicle speed characteristic data and speeding characteristic data of the target vehicle; wherein the speed characteristic data includes: the vehicle speed characteristic data and the speeding characteristic data; Extracting acceleration features according to the vehicle driving data to obtain the number of sudden accelerations and the acceleration of the target vehicle; wherein the acceleration feature data includes: the number of sudden accelerations and the acceleration; The deceleration characteristics are extracted according to the vehicle driving data to obtain the number of sudden decelerations, deceleration, number of sudden decelerations, number of high-speed continuous brakings, number of emergency stops and braking duration of the target vehicle; wherein the deceleration characteristic data includes: the number of sudden decelerations, the deceleration, the number of sudden decelerations, the number of high-speed continuous brakings, the number of emergency stops and the braking duration.

[0008] Optionally, the driving behavior characteristic data includes: energy consumption behavior characteristic data, uncivilized behavior characteristic data, and dangerous behavior characteristic data; The extracting the second feature of the vehicle driving data to obtain the driving behavior feature data includes: Energy consumption characteristics are extracted according to the vehicle driving data to obtain the air conditioning use time, low battery driving times, parking accelerator pedal times, and parking idling times; wherein the energy consumption behavior characteristic data includes: the air conditioning use time, low battery driving times, parking accelerator pedal times, and parking idling times; Uncivilized behavior features are extracted based on the vehicle driving data to obtain the number of frequent lane changes, the number of lane changes without turning on the lights, the number of turns without stopping, and the number of turns without turning on the lights; the uncivilized behavior feature data includes: the number of frequent lane changes, the number of lane changes without turning on the lights, the number of turns without stopping, and the number of turns without turning on the lights; Dangerous features are extracted based on the vehicle driving data to obtain the number of sharp turns, the number of fatigue driving, and the number of neutral coasting of the target vehicle; wherein the dangerous behavior feature data includes: the number of sharp turns, the number of fatigue driving, and the number of neutral coasting.

[0009] Optionally, the extracting a third feature from the vehicle driving data to obtain the interval feature data includes: According to the vehicle driving data, the vehicle startup time, the total vehicle power consumption, the total vehicle interval mileage and the kinetic energy recovery power of the target vehicle are calculated; wherein the interval characteristic data includes: the vehicle startup time, the total vehicle power consumption, the total vehicle interval mileage and the kinetic energy recovery power.

[0010] Optionally, the performing a fourth feature extraction on the vehicle driving data to obtain the drive motor feature data and the alarm feature data includes: Calculating the economic speed ratio of the drive motor of the target vehicle as the drive motor characteristic data according to the vehicle driving data; The number of advanced driving assistance system ADAS alarms and the number of driver monitoring system DMS alarms are extracted from the vehicle driving data as the alarm feature data.

[0011] Optionally, the driving characteristic data corresponding to the multiple dimensions include: economic dimension characteristic data, safety dimension characteristic data, control dimension characteristic data, civilization dimension characteristic data, working state dimension characteristic data, and cooperation dimension data, wherein the economic dimension characteristic data is used to characterize the energy consumption of the target vehicle, the safety dimension characteristic data is used to characterize the driving safety of the target vehicle, the control dimension characteristic data is used to characterize the vehicle control state of the target vehicle, the civilization dimension characteristic data is used to characterize whether the driving behavior of the target vehicle complies with preset civilized driving specifications, the working state dimension characteristic data is used to characterize the working state of the driver of the target vehicle, and the cooperation dimension data is used to characterize whether the driver of the target vehicle adjusts the driving behavior with reference to driving suggestions; The classifying the plurality of driving characteristic data to obtain driving characteristic data corresponding to a plurality of dimensions includes: The multiple driving characteristic data are classified to obtain the economic dimension characteristic data, the safety dimension characteristic data, the control dimension characteristic data, the civilization dimension characteristic data, the working status dimension characteristic data, and the cooperation dimension data.

[0012] Optionally, performing driving behavior evaluation on the target vehicle in each dimension according to the driving characteristic data corresponding to each dimension to obtain the driving behavior evaluation parameter of the target vehicle in each dimension includes: Calculating evaluation parameters of each driving characteristic data corresponding to each dimension respectively to obtain at least one evaluation parameter of each dimension; According to the at least one evaluation parameter of each dimension, a driving behavior evaluation parameter of each dimension is calculated.

[0013] Optionally, the sending target driving suggestion information to the user equipment according to the driving behavior evaluation parameters in the multiple dimensions includes: Calculating a target driving behavior evaluation parameter of the target vehicle according to the driving behavior evaluation parameters of the multiple dimensions; sorting the driving behavior evaluation parameters of the multiple dimensions; According to the sorted driving behavior evaluation parameters of each dimension, using the preset suggestion templates of the multiple dimensions, determining the improvement suggestion information of the target dimension in each dimension; Send improvement suggestion information of the target dimension to the user equipment.

[0014] In a second aspect, an embodiment of the present application provides a vehicle networking server, comprising: a processor and a storage medium, wherein the processor and the storage medium are connected to each other via a bus communication, the storage medium stores program instructions executable by the processor, and the processor calls the program stored in the storage medium to execute the steps of the driving behavior analysis method as described in any one of the first aspects.

[0015] Compared with the prior art, this application has the following beneficial effects: The present application provides a driving behavior analysis method and a vehicle networking server, which receives the vehicle driving data of the target vehicle uploaded by the user device in a preset historical time period; extracts features from the vehicle driving data to obtain multiple driving feature data; classifies the multiple driving feature data to obtain driving feature data corresponding to multiple dimensions; evaluates the driving behavior of the target vehicle in each dimension according to the driving feature data corresponding to each dimension to obtain the driving behavior evaluation parameters of the target vehicle in each dimension; sends target driving suggestion information to the user device according to the driving behavior evaluation parameters of multiple dimensions. Thus, statistics are taken for the driving feature data corresponding to each dimension to obtain the driving behavior evaluation parameters of each dimension, and the target driving suggestion information is generated, which can achieve a more accurate and reasonable driving behavior evaluation and effectively reflect the actual performance of each driver. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings required for use in the embodiments are briefly introduced below. It should be understood that the following drawings only show certain embodiments of the present invention and therefore should not be regarded as limiting the scope. For ordinary technicians in this field, other related drawings can be obtained based on these drawings without creative work.

[0017] Figure 1 A flowchart of a driving behavior analysis method provided in this application; Figure 2A flowchart of a method for obtaining multiple driving characteristic data provided by an embodiment of the present application; Figure 3 A schematic diagram of a flow chart of a first feature extraction method provided in an embodiment of the present application; Figure 4 A schematic diagram of a flow chart of a second feature extraction method provided in an embodiment of the present application; Figure 5 A schematic diagram of a fourth feature extraction method provided in an embodiment of the present application; Figure 6 A flowchart of a method for obtaining driving behavior evaluation parameters of a target vehicle in each dimension provided in an embodiment of the present application; Figure 7 A flowchart of a method for obtaining and sending target driving suggestion information provided in an embodiment of the present application; Figure 8 A schematic diagram of a driving behavior analysis device provided in an embodiment of the present application; Fig. 9 A schematic diagram of an Internet of Vehicles server provided in an embodiment of the present application.

[0018] Icon: 801 - receiving module, 802 - extraction module, 803 - classification module, 804 - evaluation module, 805 - sending module, 901 - processor, 902 - storage medium. DETAILED DESCRIPTION

[0019] In order to make the purpose, technical scheme and advantages of the embodiments of the present invention clearer, the technical scheme in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are part of the embodiments of the present application, rather than all the embodiments. The components of the embodiments of the present application described and shown in the drawings here can be arranged and designed in various different configurations.

[0020] Therefore, the following detailed description of the embodiments of the present application provided in the accompanying drawings is not intended to limit the scope of the present application for protection, but merely represents selected embodiments of the present application. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present application.

[0021] It should be noted that similar reference numerals and letters denote similar items in the following drawings, and therefore, once an item is defined in one drawing, further definition and explanation thereof is not required in subsequent drawings.

[0022] In addition, the terms “first”, “second”, etc., if used, are merely used to distinguish between the descriptions and should not be understood as indicating or implying relative importance.

[0023] It should be noted that, in the absence of conflict, the features in the embodiments of the present invention may be combined with each other.

[0024] The following is an explanation of a driving behavior analysis method provided by the present application through a specific example. Figure 1 This is a flow chart of a driving behavior analysis method provided in this application. The execution subject of this method is a car networking server, which has computing and processing functions. Figure 1 As shown, the method includes: S101: Receive vehicle driving data of a target vehicle in a preset historical time period uploaded by a user device.

[0025] The user device on the target vehicle uploads the vehicle driving data to the Internet of Vehicles server. The user device can be a user's mobile phone device or computer device.

[0026] For example, the preset historical time period can be the driving time period of the same driver (the time from the start of driving to the end of driving), or it can be a time period set by the user (for example, within a certain day, within a certain week, or within a certain month). When segmenting vehicle driving data, the embodiment of the present application not only considers the vehicle status from each ignition to shutdown of the vehicle, but also considers the driver corresponding to the trip. When the vehicle changes the driver, it is considered that the previous trip is over; when the trip segmentation is not avoided, the scenario judgment that the driver's driving time exceeds 4 hours and the rest time is less than 20 minutes is lost. When the trip is segmented, the vehicle is turned off for more than 20 minutes, and the previous trip is considered to be over. In order to avoid the problem of cross-day driving data of vehicles with bad driving behavior, the cross-day trip is split twice, split into two trips before and after zero o'clock.

[0027] For example, vehicle driving data includes at least: vehicle identification, data collection time, data type, data storage time, vehicle status, charging status, operating mode, vehicle speed, cumulative mileage, total voltage, total current, SOC (‌ remaining power, StateOf Charge), DC (Driving Cycle) status, gear position, braking force, driving force, insulation resistance, accelerator pedal travel value, brake pedal status, air conditioning status, positioning coordinates (GPS positioning coordinates, or Beidou positioning coordinates), ADAS alarm times and DMS alarm times. Vehicle driving data is various types of data corresponding to each data collection time stored in real time.

[0028] S102: Extract features from vehicle driving data to obtain a plurality of driving feature data.

[0029] Vehicle driving data is the original data of driving. If the vehicle driving data is directly used for analysis, the analysis result will be inaccurate. Therefore, feature extraction is performed on the vehicle driving data to obtain multiple driving feature data. Using the driving feature data for analysis will make the analysis result more accurate.

[0030] S103: Classify the multiple driving characteristic data to obtain driving characteristic data corresponding to multiple dimensions.

[0031] Categorizing multiple driving characteristic data into multiple dimensions facilitates more sophisticated evaluation from multiple dimensions.

[0032] S104. According to the driving characteristic data corresponding to each dimension, a driving behavior evaluation is performed on the target vehicle in each dimension to obtain a driving behavior evaluation parameter of the target vehicle in each dimension.

[0033] Each dimension corresponds to multiple driving characteristic data. By analyzing and calculating the multiple driving characteristic data, the driving behavior evaluation parameters of the target vehicle in each dimension are obtained.

[0034] S105: Send target driving suggestion information to the user device according to the driving behavior evaluation parameters in multiple dimensions.

[0035] The driving behavior of the driver has been accurately reflected through the driving behavior evaluation parameters of multiple dimensions. In order to provide accurate suggestions to the driver, target driving suggestion information is generated based on the driving behavior evaluation parameters of multiple dimensions and sent to the user device.

[0036] Therefore, by statistically analyzing the driving characteristic data corresponding to each dimension, obtaining the driving behavior evaluation parameters for each dimension, and generating target driving recommendation information, a more accurate and reasonable driving behavior evaluation can be achieved, effectively reflecting the actual performance of each driver.

[0037] In summary, in this embodiment, the vehicle driving data of the target vehicle in the preset historical time period uploaded by the user device is received; the vehicle driving data is feature extracted to obtain multiple driving feature data; the multiple driving feature data are classified to obtain driving feature data corresponding to multiple dimensions; according to the driving feature data corresponding to each dimension, the driving behavior of the target vehicle is evaluated in each dimension to obtain the driving behavior evaluation parameters of the target vehicle in each dimension; according to the driving behavior evaluation parameters of multiple dimensions, the target driving suggestion information is sent to the user device. Therefore, the driving feature data corresponding to each dimension is counted, the driving behavior evaluation parameters of each dimension are obtained, and the target driving suggestion information is generated, which can achieve a more accurate and reasonable driving behavior evaluation and effectively reflect the actual performance of each driver.

[0038] Furthermore, in another embodiment of the present application, before extracting features from the vehicle driving data, the vehicle driving data is first cleaned to remove the vehicle stalling data in the vehicle driving data to avoid the impact of the stalling data on the calculation; refer to the data requirements for vehicles in GB / T 32960 or enterprise standards to remove abnormal values ​​from the feature data; perform data variable verification on continuous data such as vehicle speed, mileage, SOC, etc. to determine whether the data jumps, and re-interpolate the jump value. For example, for data with an interval of 1 second, the vehicle speeds are 50km / h and 52km / h respectively, and the mileage difference is greater than 1km, which means that the mileage data has abnormally jumped, and the mileage value needs to be re-interpolated. Delete invalid trips with a driving time of less than 10 minutes or a driving distance of less than 2 kilometers.

[0039] In the above Figure 1 On the basis of the corresponding embodiment, the embodiment of the present application also provides a method for obtaining multiple driving characteristic data. Figure 2 A flow chart of a method for obtaining multiple driving characteristic data provided by an embodiment of the present application. Figure 2 As shown, the multiple driving characteristic data include: motion characteristic data, driving behavior characteristic data, interval characteristic data, drive motor characteristic data, and alarm characteristic data; In S102, feature extraction is performed on the vehicle driving data to obtain a plurality of driving feature data, including: S201. Perform a first feature extraction on vehicle driving data to obtain motion feature data.

[0040] S202: Perform a second feature extraction on the vehicle driving data to obtain driving behavior feature data.

[0041] S203: extract the third feature of the vehicle driving data to obtain interval feature data.

[0042] S204 , extracting the fourth feature of the vehicle driving data to obtain driving motor feature data and alarm feature data.

[0043] In summary, in this embodiment, multiple driving characteristic data include: motion characteristic data, driving behavior characteristic data, interval characteristic data, drive motor characteristic data, and alarm characteristic data; a first feature extraction is performed on the vehicle driving data to obtain motion characteristic data; a second feature extraction is performed on the vehicle driving data to obtain driving behavior characteristic data; a third feature extraction is performed on the vehicle driving data to obtain interval characteristic data; a fourth feature extraction is performed on the vehicle driving data to obtain drive motor characteristic data and alarm characteristic data.

[0044] In the above Figure 2 On the basis of the corresponding embodiment, the embodiment of the present application also provides a first feature extraction method. Figure 3 A schematic diagram of a first feature extraction method provided in an embodiment of the present application. Figure 3 As shown, the motion characteristic data includes: speed characteristic data, acceleration characteristic data, and deceleration characteristic data. In S201, the first feature extraction is performed on the vehicle driving data to obtain motion feature data, including: S301. Extract speed characteristics based on vehicle driving data to obtain speed characteristic data and speeding characteristic data of the target vehicle.

[0045] The speed characteristic data includes: vehicle speed characteristic data and speeding characteristic data.

[0046] The speed characteristic data includes: average driving speed, speed mean square deviation, and duration of non-zero speed. The average speed reflects the driver's driving skills and is calculated by dividing the sum of all non-zero speeds by the number of non-zero speed reports. The speed mean square deviation is calculated by taking the mean square deviation of all non-zero speed data. The discrete degree of speed reflects the stability of the driving process.

[0047] The speeding characteristic data includes: speeding duration, speeding ratio, speeding threshold, and speeding times. The speeding ratio represents the proportion of different speeding ratios in all speeding vehicles.

[0048] The vehicle speed is determined to be overspeeding when it is greater than the speeding threshold. The overspeeding duration includes: the duration of each overspeeding period and the total overspeeding duration. The overspeeding ratio is the ratio of the maximum speed in each overspeeding period to the speed threshold. The number of overspeeding times is the sum of the number of overspeeding periods.

[0049] Specifically, the average driving speed, the mean square error of the speed, and the duration when the speed is not zero are calculated based on the speed at each data collection time in the vehicle driving data, and the speeding duration, speeding ratio, and number of speeding times are calculated based on the speed limit value of each positioning coordinate.

[0050] S302: Extract acceleration features based on vehicle driving data to obtain the number of rapid accelerations and acceleration of the target vehicle.

[0051] The acceleration characteristic data includes: the number of rapid accelerations and the acceleration.

[0052] The acceleration characteristic data can characterize the driver's driving style. The number of rapid accelerations is the number of times the acceleration threshold is exceeded, and the acceleration is the maximum acceleration in each acceleration period.

[0053] For example, the vehicle speed is greater than the vehicle speed threshold (for example, 40km / h) and (the vehicle has driving force or there is accelerator pedal data), and the data is segmented. If the interval between adjacent time periods is less than the threshold, they are merged into the same time period. If the acceleration of adjacent data within this time period is greater than the acceleration threshold (1.38m / s^2) for 2 consecutive seconds, it is recorded as one occurrence. Speed ​​screening solves problems such as unstable acceleration at low speeds. If the vehicle has driving force / accelerator pedal, instantaneous acceleration scenes such as steep slopes can be eliminated.

[0054] Specifically, the number of rapid accelerations and the acceleration are calculated according to the vehicle speed at each data collection time in the vehicle driving data.

[0055] S303, extracting deceleration features according to the vehicle driving data to obtain the number of rapid decelerations, deceleration, number of sharp decelerations, number of high-speed continuous brakings, number of emergency stops, and braking duration of the target vehicle.

[0056] Among them, the deceleration characteristic data includes: number of sudden decelerations, deceleration rate, number of sudden decelerations, number of high-speed continuous braking, number of emergency stops and braking duration.

[0057] The number of sudden decelerations is the number of times the first dangerous deceleration threshold is exceeded, and the deceleration is the first deceleration that exceeds the dangerous deceleration threshold. The number of sudden decelerations is the number of times the second dangerous deceleration threshold is exceeded, and the number of high-speed continuous brakings is the number of times the high-speed threshold is exceeded and the continuous braking threshold is exceeded. The number of emergency brake stops is the number of times the brake pedal state exceeds the brake stop threshold, and the braking duration includes: the duration of each brake and the total braking duration.

[0058] For example, for sudden deceleration, the vehicle speed is greater than the threshold (40km / h) and (the vehicle has braking force or brake pedal data exists), and the data is segmented. If the interval between adjacent time periods is less than the threshold, they are merged into the same time period. If the deceleration of adjacent data within this time period is less than the acceleration threshold (-1.2m / s^2) for 2 consecutive seconds, it is recorded as 1 occurrence. Number of sudden decelerations: the sum of the number of deceleration periods that meet the above requirements. Deceleration: the maximum deceleration of each deceleration period.

[0059] For example, for sudden deceleration, the vehicle speed is greater than 20km / h and the brake pedal data is greater than 50%, and it lasts for more than 2 seconds. If the interval between adjacent time periods exceeds 3 seconds, they are considered to be different time periods. Number of sudden decelerations: The sum of the number of deceleration periods that meet the above requirements.

[0060] For example, for high-speed continuous braking, the vehicle speed is greater than 40km / h and exceeds the braking number threshold (for example, 5 times) within a fixed time (for example, 30s). Filter the data with a speed greater than the threshold (40km / h) and perform data segmentation processing. If the interval between adjacent time periods is less than the time threshold, they are merged into the same time period. The number of braking times greater than the braking number threshold in this time period is recorded as 1 occurrence. High-speed continuous braking times: the sum of the times in the time periods that meet the above requirements.

[0061] For example, for emergency braking, filter the data with a speed greater than 40km / h and brake pedal data greater than 0. If the interval data of adjacent time periods is less than 3 seconds, the adjacent time periods are merged into the same time period. If the speed does not drop to 0km / h between adjacent time periods, discard the interval data. Otherwise, calculate whether the interval data drops from 40km / h to 0km / h for continuous braking. If the continuous braking rate is >0.85 and the deceleration within the time period is less than the deceleration threshold (-1.2m / s^2), it is considered an emergency brake. Number of emergency brakes: the sum of the number of time periods that meet the above requirements. Braking period: the period when the vehicle is in working condition and the speed is greater than 0km / h and the brake pedal data is greater than 0. Braking duration: the sum of the time periods that meet the above requirements.

[0062] Specifically, the number of sudden decelerations, deceleration, number of sharp decelerations, number of high-speed continuous braking, number of emergency stops and braking duration are calculated based on the vehicle speed and brake pedal status at each data collection time in the vehicle driving data.

[0063] In summary, in this embodiment, the motion feature data includes: speed feature data, acceleration feature data, and deceleration feature data; speed feature extraction is performed based on the vehicle driving data to obtain the vehicle speed feature data and speeding feature data of the target vehicle; wherein, the speed feature data includes: vehicle speed feature data and speeding feature data; acceleration feature extraction is performed based on the vehicle driving data to obtain the number of sudden accelerations and acceleration of the target vehicle; wherein, the acceleration feature data includes: the number of sudden accelerations and acceleration; deceleration feature extraction is performed based on the vehicle driving data to obtain the number of sudden decelerations, deceleration, number of sudden decelerations, number of high-speed continuous brakings, number of emergency stops, and braking duration of the target vehicle; wherein, the deceleration feature data includes: the number of sudden decelerations, deceleration, number of sudden decelerations, number of high-speed continuous brakings, number of emergency stops, and braking duration. Thus, the motion feature data can be accurately extracted.

[0064] In the above Figure 2 On the basis of the corresponding embodiment, the embodiment of the present application also provides a second feature extraction method. Figure 4 A schematic diagram of a second feature extraction method provided in an embodiment of the present application. Figure 4As shown, the driving behavior characteristic data includes: energy consumption behavior characteristic data, uncivilized behavior characteristic data, and dangerous behavior characteristic data.

[0065] The second feature extraction is performed on the vehicle driving data in S202 to obtain driving behavior feature data, including: S401, extracting energy consumption characteristics based on vehicle driving data to obtain air conditioning usage time, low battery driving times, parking accelerator pedal times, and parking idling times.

[0066] Among them, the energy consumption behavior characteristic data include: the length of time the air conditioner is used, the number of times the battery is low, the number of times the accelerator is pressed when parked, and the number of times the car is idling when parked.

[0067] The air conditioning usage time includes: the usage time of each time and the total usage time of the air conditioning, which reflects the energy consumption of the air conditioning.

[0068] In addition to the number of low-battery driving times, the duration of each low-battery driving is also included. Low-battery driving will reduce battery life. If the vehicle SOC is less than 20% and the speed is not 0 and the duration is greater than 5 minutes, it is considered low-battery driving. Number of low-battery driving times: the number of times the above behavior occurs.

[0069] In addition to the number of times the accelerator is pressed when the vehicle is parked, the duration of the accelerator is also included. Pressing the accelerator when the vehicle is parked increases the vehicle's energy consumption. Pressing the accelerator when the vehicle is parked: The vehicle is in working state (there is driving force or the accelerator pedal data is greater than 0), and the duration of this state is greater than or equal to the time threshold. First, select the target data that meets the above conditions and perform data segmentation processing. If the interval data of adjacent time periods shows that the vehicle is not turned off and the gear is in neutral, the adjacent time periods are merged into the same time period, and the duration of this time period is greater than the time threshold (1min) and is recorded as 1 event occurrence.

[0070] Parking idling reflects the parking or traffic congestion during driving. Parking idling: The vehicle is in working state and the speed is 0 (no driving force / accelerator pedal data is 0) and the motor state is working. If the state lasts longer than the time threshold (1min), it is recorded as 1 event. The idling time must also be recorded.

[0071] Specifically, based on the data collection time, vehicle status, charging status, operating mode, vehicle speed, SOC, gear position, accelerator pedal travel value, and air conditioning status, the air conditioning usage time, low-battery driving times, parking accelerator pedal times, and parking idling times are calculated.

[0072] S402, extract uncivilized features based on vehicle driving data to obtain the number of frequent lane changes, the number of lane changes without turning on the lights, the number of turns without stopping, and the number of turns without turning on the lights.

[0073] Among them, the uncivilized behavior characteristic data include: the number of frequent lane changes, the number of lane changes without turning on the lights, the number of turns without stopping, and the number of turns without turning on the lights. The uncivilized behavior characteristic data reflects whether the driver drives the vehicle steadily.

[0074] For example, for frequent lane changes, the road map point sequence is obtained based on the vehicle's driving positioning coordinates, and the vehicle steering is fitted or the vehicle steering data stored in the road map is used to determine whether the vehicle changes lanes. Except for the intersection position, if the steering difference is greater than the lane change steering threshold, the vehicle is considered to have changed lanes. If the number of lane changes within the distance of its vehicle length*n is greater than the lane change number threshold, it is recorded as 1 event. The number of frequent lane changes is the number of times the above events occur.

[0075] For example, for lane change without turning on the lights, when the vehicle determines that the current behavior is lane change and does not turn on the turn signal, it is recorded as 1 event. The number of lane change without turning on the lights is the number of times the above event occurs.

[0076] For example, for turning without stopping, according to the road traffic rule of "must stop when turning right" for heavy trucks, the road map is combined to monitor whether the vehicle position is an intersection and whether the vehicle steering wheel has a value greater than the threshold. If the vehicle position is at an intersection, the steering wheel is turned right and the value is greater than the threshold but the vehicle does not stop to wait, it is recorded as 1 event. The number of turning without stopping is the number of times the above events occur.

[0077] For example, for turning without turning on the lights, the road map is combined to monitor whether the vehicle position is an intersection and whether the vehicle steering wheel has a value greater than the threshold. If the vehicle position is at an intersection and the steering wheel is greater than the threshold but the turn signal is not on, it is recorded as 1 event. The number of turning without turning on the lights is the number of times the above event occurs.

[0078] Specifically, the number of frequent lane changes, the number of lane changes without turning on the lights, the number of turns without stopping, and the number of turns without turning on the lights are calculated based on the data collection time, vehicle status, operating mode, vehicle speed, gear, braking force, driving force, accelerator pedal travel value, brake pedal status, and positioning coordinates.

[0079] S403: extracting dangerous features according to the vehicle driving data to obtain the number of sharp turns, fatigue driving, and neutral coasting of the target vehicle.

[0080] Among them, the dangerous behavior characteristic data include: number of sharp turns, number of fatigue driving, and number of neutral sliding times.

[0081] For example, for a sharp turn, the map is combined to monitor whether the vehicle position is an intersection, monitor whether the vehicle decelerates within a specified range at the target position, and the speed exceeds the threshold within the specified area as 1 time. The number of sharp turns is the number of times the above events occur.

[0082] For example, for fatigue driving, if the driver drives the vehicle continuously for more than 4 hours and does not stop to rest as reminded, exceeding the reminder time threshold, it is recorded as 1 event. The number of fatigue driving times is the number of times the above event occurs.

[0083] For example, for neutral coasting, when the driver is driving the vehicle, the vehicle speed is greater than 0, the gear is in neutral, and the duration of this state is greater than the preset coasting duration, and the condition is met and recorded as 1 event. The number of neutral coasting times is the number of times the above events occur.

[0084] Specifically, the number of sharp turns, the number of fatigue driving, and the number of neutral coasting are calculated based on the data collection time, vehicle status, operating mode, vehicle speed, gear position, braking force, driving force, accelerator pedal travel value, brake pedal status, and positioning coordinates.

[0085] In summary, in this embodiment, the driving behavior characteristic data includes: energy consumption behavior characteristic data, uncivilized behavior characteristic data, and dangerous behavior characteristic data; energy consumption characteristics are extracted according to the vehicle driving data to obtain the air conditioning use time, low battery driving times, parking accelerator times, and parking idling times; wherein, the energy consumption behavior characteristic data includes: air conditioning use time, low battery driving times, parking accelerator times, and parking idling times; uncivilized characteristics are extracted according to the vehicle driving data to obtain the number of frequent lane changes, the number of lane changes without turning on the lights, the number of turns without stopping, and the number of turns without turning on the lights; uncivilized behavior characteristic data include: frequent lane changes, the number of lane changes without turning on the lights, the number of turns without stopping, and the number of turns without turning on the lights; dangerous characteristics are extracted according to the vehicle driving data to obtain the number of sharp turns, fatigue driving, and neutral coasting times of the target vehicle; wherein, the dangerous behavior characteristic data include: the number of sharp turns, fatigue driving, and neutral coasting times. Thus, the driving behavior characteristic data is accurately extracted.

[0086] In the above Figure 2 On the basis of the corresponding embodiment, in another embodiment of the present application, the third feature extraction is performed on the vehicle driving data in S203 to obtain the interval feature data, including: According to the vehicle driving data, the vehicle start-up time, total vehicle power consumption, total vehicle mileage and kinetic energy recovery power of the target vehicle are calculated.

[0087] Among them, the interval characteristic data include: vehicle start-up time, vehicle total power consumption, vehicle total interval mileage and kinetic energy recovery power.

[0088] For example, the vehicle startup time is the total time the vehicle is in working condition, the vehicle's total power consumption is the total value of the vehicle's energy consumption reduction within a preset historical time period, the vehicle's total interval mileage is the total value of the vehicle's energy consumption reduction within a preset historical time period, and the kinetic energy recovery power is the SOC growth value when the vehicle is in driving condition.

[0089] Specifically, the vehicle start-up time, total power consumption, total mileage and kinetic energy recovery power are calculated based on the vehicle identification, data collection time, vehicle status, charging status, operating mode, cumulative mileage, total voltage, total current and SOC.

[0090] In summary, in this embodiment, based on the vehicle driving data, the vehicle start-up time, total vehicle power consumption, total vehicle interval mileage, and kinetic energy recovery power of the target vehicle are calculated; wherein the interval characteristic data includes: vehicle start-up time, total vehicle power consumption, total vehicle interval mileage, and kinetic energy recovery power. Thus, the interval characteristic data is accurately extracted.

[0091] In the above Figure 2 On the basis of the corresponding embodiment, the embodiment of the present application also provides a fourth feature extraction method. Figure 5 A schematic diagram of a fourth feature extraction method provided in an embodiment of the present application. Figure 5 As shown, in S204, the fourth feature extraction is performed on the vehicle driving data to obtain the driving motor feature data and the alarm feature data, including: S501. Calculate the economic speed ratio of the drive motor of the target vehicle according to the vehicle driving data as the drive motor characteristic data.

[0092] The characteristic data of the driving motor is the economic speed ratio, which is obtained according to the ratio of the number of economic speeds of the driving motor to the total number of speeds. For example, the economic speed range is a preset speed range, and if one motor rotation is within the economic speed range, it is determined to be an economic speed.

[0093] S502 : Extracting the number of ADAS alarms and the number of DMS alarms from the vehicle driving data as alarm feature data.

[0094] In summary, in this embodiment, based on the vehicle driving data, the economic speed ratio of the drive motor of the target vehicle is calculated as the drive motor characteristic data; and the number of ADAS alarms and the number of DMS alarms are extracted from the vehicle driving data as the alarm characteristic data. Thus, the drive motor characteristic data and the alarm characteristic data are accurately extracted.

[0095] In the above Figure 1On the basis of the corresponding embodiments, in another embodiment of the present application, the driving characteristic data corresponding to the multiple dimensions include: economic dimension characteristic data, safety dimension characteristic data, control dimension characteristic data, civilization dimension characteristic data, working state dimension characteristic data, and cooperation degree dimension data, wherein the economic dimension characteristic data is used to characterize the energy consumption of the target vehicle, the safety dimension characteristic data is used to characterize the driving safety of the target vehicle, the control dimension characteristic data is used to characterize the vehicle control state of the target vehicle, the civilization dimension characteristic data is used to characterize whether the driving behavior of the target vehicle complies with the preset civilized driving specifications, the working state dimension characteristic data is used to characterize the working state of the driver of the target vehicle, and the cooperation degree dimension data is used to characterize whether the driver of the target vehicle adjusts the driving behavior with reference to the driving suggestions; In S103, the plurality of driving characteristic data are classified to obtain driving characteristic data corresponding to a plurality of dimensions, including: The multiple driving characteristic data are classified to obtain economic dimension characteristic data, safety dimension characteristic data, control dimension characteristic data, civilization dimension characteristic data, working status dimension characteristic data, and cooperation dimension data.

[0096] The characteristic data of the economic dimension include at least: the total power consumption of the vehicle, the usage time of the air conditioner, the number of parking and idling times, and the amount of kinetic energy recovered.

[0097] The safety dimension characteristic data includes at least: number of ADAS alarms, number of DMS alarms, number of sudden accelerations, number of sudden decelerations, and number of sharp turns.

[0098] The control dimension characteristic data include: average driving speed, speed mean square deviation, length of time when the speed is not 0, length of time when the speed exceeds the speed limit, speeding ratio, speeding threshold, number of speeding times, number of sudden accelerations, acceleration, number of sudden decelerations, deceleration, number of sudden decelerations, number of continuous high-speed braking, number of emergency stops, braking duration, number of sharp turns, and drive motor characteristic data.

[0099] The characteristic data of the civilization dimension include: the number of frequent lane changes, the number of lane changes without turning on the lights, the number of turns without stopping, the number of turns without turning on the lights, the number of sharp turns, the number of fatigue driving, and the number of neutral gear coasting.

[0100] The characteristic data of the work status dimension include: working hours and leave data.

[0101] The cooperation dimension data includes: the change in driving score.

[0102] In the above Figure 1 On the basis of the corresponding embodiment, the embodiment of the present application also provides a method for obtaining the driving behavior evaluation parameters of the target vehicle in each dimension. Figure 6A flow chart of a method for obtaining driving behavior evaluation parameters of a target vehicle in each dimension provided in an embodiment of the present application. Figure 6 As shown, in S104, according to the driving characteristic data corresponding to each dimension, the driving behavior of the target vehicle is evaluated in each dimension to obtain the driving behavior evaluation parameters of the target vehicle in each dimension, including: S601. Calculate evaluation parameters of each driving characteristic data corresponding to each dimension respectively to obtain at least one evaluation parameter of each dimension.

[0103] For example, for the economic dimension, the calculation method of the braking time evaluation parameter is: C1=A10*T10. Among them, C1 is the braking time evaluation parameter, A10 is the braking time evaluation parameter, and T10 is the braking time evaluation parameter coefficient. The calculation method of the braking time evaluation parameter is: A10=1-F15 / F3. Among them, F15 is the braking time, and F3 is the time when the vehicle speed is not zero.

[0104] The calculation method of the energy-consuming driving behavior evaluation parameter is: C2=ΣAn*Tn, n=11, 12, 13, 14. Among them, C2 is the energy-consuming driving behavior evaluation parameter, A11 is the air conditioning use time evaluation parameter, A12 is the idling time evaluation parameter, A13 is the parking accelerator time evaluation parameter, A14 is the low-battery driving times evaluation parameter, T11 is the air conditioning use time evaluation parameter coefficient, T12 is the idling time evaluation parameter coefficient, T13 is the parking accelerator time evaluation parameter coefficient, and T14 is the low-battery driving times evaluation parameter coefficient.

[0105] The calculation method of energy consumption evaluation parameters is: C3=A22*T22. Among them, C3 is the energy consumption evaluation parameter, A22 is the energy consumption value, and T22 is the energy consumption value coefficient. A22=1-F27 / F28*100 / 100km energy consumption threshold, F27 is the total energy consumption, and F28 is the total interval mileage.

[0106] The calculation method of the kinetic energy recovery evaluation parameter is: C4=A24*T24 / 100. Among them, C4 is the kinetic energy recovery evaluation parameter, A24 is the kinetic energy recovery power, and T24 is the kinetic energy recovery power coefficient.

[0107] For example, for the safety dimension, the calculation method of the overspeed control evaluation parameter is: C5=A2*T2. Among them, C5 is the overspeed control evaluation parameter, A2 is the overspeed control value, and T2 is the overspeed control value coefficient. A2=F4 / F3*(1-overspeed ratio sum), F4 is the overspeed duration, and F3 is the duration of the vehicle speed not being zero.

[0108] The calculation method of the acceleration control evaluation parameter is: C6=A4*T4. Among them, C6 is the acceleration control evaluation parameter, A4 is the acceleration value, T4 is the acceleration value coefficient, A4=1-ΣF9 / F8 / acceleration threshold, F8 is the number of rapid accelerations, and F9 is the acceleration.

[0109] The calculation method of the deceleration control evaluation parameter is: C7=A6*T6. Among them, C7 is the deceleration control evaluation parameter, A6 is the deceleration value, T6 is the deceleration value coefficient, A6=1-ΣF11 / F10 / acceleration threshold, F10 is the number of rapid decelerations, and F11 is the deceleration.

[0110] The calculation method of the risk behavior assessment parameters is: C8=ΣAn*Tn, n=18, 19, 20. Among them, A18 is the sharp turn value, T18 is the sharp turn value coefficient, A19 is the fatigue driving value, T19 is the fatigue driving value coefficient, A20 is the neutral coasting value, and T20 is the neutral coasting value coefficient. A18=1-F23 / number threshold, F23 is the number of sharp turns, A19=1-F24 / number threshold, F24 is the number of fatigue driving, A20=1-F25 / number threshold, F25 is the number of neutral coasting.

[0111] The calculation method of ADAS alarm evaluation parameters is: C9=ΣAn*Tn, n=26, 27, 28. Among them, A26 is the front collision warning value, T26 is the front collision warning value coefficient, A27 is the lane departure warning value, T27 is the lane departure warning value coefficient, A28 is the pedestrian detection and collision warning value, T28 is the pedestrian detection and collision warning value coefficient. A26=1-F31 / number threshold, F31 is the number of front collision warnings, A27=1-F32 / number threshold, F32 is the number of lane departure warnings, A28=1-F33 / number threshold, F33 is the number of pedestrian detection and collision warnings.

[0112] The calculation method of DMS alarm evaluation parameters is: C10=ΣAn*Tn, n=29, 30, 31, 32, 33, 35, 36, 37, 38, 39. Among them, A29 is the yawning alarm value, T29 is the yawning alarm value coefficient, A30 is the hands off the steering wheel alarm value, T30 is the hands off the steering wheel alarm value coefficient, A31 is the seat belt not fastened alarm value, T31 is the seat belt not fastened alarm value coefficient, A32 is the distraction alarm value, T32 is the distraction alarm value coefficient, A33 is the looking around alarm value, T33 is the looking around alarm value coefficient, A35 is the smoking alarm value, T35 is the smoking alarm value coefficient, A36 is the phone call alarm value, T36 is the phone call alarm value coefficient, A37 is the mobile phone playing while driving alarm value, T37 is the mobile phone playing while driving alarm value coefficient, A38 is the camera occlusion alarm value, T38 is the camera occlusion alarm value coefficient, A39 is the wearing anti-infrared black mirror reminder value, T39 is the wearing anti-infrared black mirror reminder value coefficient. A29=1-F34 / times threshold, F34 is the number of yawning alarms, A30=1-F35 / times threshold, F35 is the number of hands off the steering wheel alarms, A31=1-F36 / times threshold, F36 is the number of seat belt not fastened alarms, A32=1-F37 / times threshold, F37 is the number of distraction alarms, A33=1-F38 / times threshold, F38 is the number of looking around alarms, A35=1-F40 / times threshold, F40 is the number of smoking alarms, A36=1-F41 / times threshold, F41 is the number of phone calls alarms, A37=1-F42 / times threshold, F42 is the number of playing with mobile phones while driving alarms, A38=1-F43 / times threshold, F43 is the number of camera occlusion alarms, A39=1-F44 / times threshold, F44 is the number of reminders for wearing anti-infrared black glasses.

[0113] For example, for the control dimension, the calculation method of the vehicle speed control evaluation parameter is: C11=A1*T1. Among them, C11 is the vehicle speed control evaluation parameter, A1 is the vehicle speed value, T1 is the vehicle speed value coefficient, A1=F1 / F7*G1+(F1-F2) / F1*G2, F1 is the average driving speed, G1 is the average driving speed coefficient, F2 is the speed mean square deviation, G2 is the speed mean square deviation coefficient, and F7 is the speeding threshold.

[0114] The calculation method of the acceleration times control evaluation parameter is: C12=A3*T3. Among them, C12 is the acceleration times control evaluation parameter, A3 is the sudden acceleration value, T3 is the sudden acceleration value coefficient, A3=1-F8 / times threshold, and F8 is the sudden acceleration times.

[0115] The calculation method of the deceleration times control evaluation parameter is: C13=A5*T5. Among them, C13 is the deceleration times control evaluation parameter, A5 is the rapid deceleration value, T5 is the rapid deceleration value coefficient, A5=1-F10 / times threshold, and F10 is the rapid deceleration times.

[0116] The calculation method of the motor control evaluation parameter is: C14=A25*T25. Among them, C14 is the motor control evaluation parameter, A25 is the economic speed duration value, T25 is the economic speed duration value coefficient, A25= F30 / F26, F26 is the vehicle startup duration, and F30 is the economic speed duration.

[0117] For example, for the civilization dimension, the calculation method of the uncivilized driving behavior evaluation parameter is: C15=ΣAn*Tn, n=15, 16, 17. Among them, C13 is the uncivilized driving behavior evaluation parameter, A15 is the frequent lane change value, T15 is the frequent lane change value coefficient, A16 is the turn stop value, T16 is the turn stop value coefficient, A17 is the turn without light value, T17 is the turn without light value coefficient. A15=1-F20 / number threshold, F20 is the number of frequent lane changes, A16=1-F21 / number threshold, F21 is the number of turn stops, A17=1-F22 number threshold, F22 is the number of turn without light.

[0118] For example, for the working status dimension, the calculation method of the driving time evaluation parameter is: C16= A21*T21, C16 is the driving time evaluation parameter, A21 is the driving time, T21 is the driving time coefficient, A21=F26 / scoring time hours*24 / daily working time threshold, and F26 is the vehicle startup time.

[0119] The calculation method of DMS-away alarm evaluation parameters is: C17= A34*T34, A34 is the away alarm value, T34 is the away alarm value coefficient, A34=1-F39 / number threshold, F39 is the number of away alarms.

[0120] For example, for the cooperation dimension, the calculation method of the month-on-month driver score difference evaluation parameter is: C18 = ((the score of the rectification item in this month - the score of the rectification item in the previous month) > 0) number and / number of rectification items. C18 is the month-on-month driver score difference evaluation parameter.

[0121] S602: Calculate a driving behavior evaluation parameter of each dimension according to at least one evaluation parameter of each dimension.

[0122] For each evaluation parameter of each dimension, there is a corresponding evaluation parameter coefficient. In one dimension, each evaluation parameter coefficient is used to perform weighted calculation on each evaluation parameter to obtain the driving behavior evaluation parameter of the dimension.

[0123] In summary, in this embodiment, the evaluation parameters of each driving characteristic data corresponding to each dimension are calculated respectively to obtain at least one evaluation parameter of each dimension; and the driving behavior evaluation parameter of each dimension is calculated according to at least one evaluation parameter of each dimension. Thus, by performing detailed statistical calculations on each dimension and providing different calculation methods for different characteristic data, a more accurate and reasonable driving behavior evaluation can be achieved, which effectively reflects the actual performance and specific improvement needs of each driver.

[0124] In the above Figure 1 On the basis of the corresponding embodiment, the embodiment of the present application also provides a method for obtaining and sending target driving suggestion information. Figure 7 A flowchart of a method for obtaining and sending target driving suggestion information provided by an embodiment of the present application. Figure 7 As shown, in S105, target driving suggestion information is sent to the user device according to the driving behavior evaluation parameters of multiple dimensions, including: S701. Calculate target driving behavior evaluation parameters of a target vehicle according to driving behavior evaluation parameters of multiple dimensions.

[0125] For each dimension of driving behavior evaluation parameter, there is a corresponding driving behavior evaluation parameter coefficient. A weighted calculation is performed based on each driving behavior evaluation parameter and the corresponding evaluation parameter coefficient to obtain a target driving behavior evaluation parameter of the target vehicle.

[0126] The target driving behavior evaluation parameter of the target vehicle can reflect the driving level of the driver. For example, if the target driving behavior evaluation parameter is greater than the first threshold, it indicates that the driver's driving level is superb; if the target driving behavior evaluation parameter is greater than the second threshold and less than or equal to the first threshold, it indicates that the driver's driving level is average; if the target driving behavior evaluation parameter is greater than the third threshold and less than or equal to the second threshold, it indicates that the driver's driving level is poor.

[0127] S702: Sort driving behavior evaluation parameters in multiple dimensions.

[0128] For example, the driving behavior evaluation parameters of multiple dimensions are sorted from low to high according to parameter values.

[0129] S703: According to the sorted driving behavior evaluation parameters of each dimension, a preset suggestion template of multiple dimensions is used to determine improvement suggestion information of a target dimension in each dimension.

[0130] For example, the higher the ranking of a dimension, the lower the driving behavior evaluation parameter of the dimension, and the lower the ranking of the dimension, the better the recommendations will be made first.

[0131] For example, if the driving behavior evaluation parameters of each dimension are low, other dimensions can be linked to make suggestions. For example: when the energy consumption parameter in the economic dimension is low, the vehicle speed control and motor control in the control dimension can be linked to make adjustments; when the safety dimension parameter is low, the driving control acceleration and deceleration times can be linked to make adjustments. For example, the target driving behavior evaluation parameter of the target vehicle is calculated to be 80 points, including 70 points for economic behavior, 89 points for safety behavior, 70 points for driving control, 67 points for civilized driving, 85 points for working status, and 100 points for cooperation. When making suggestions to the driver, first sort the driving behavior evaluation parameters of the six dimensions from low to high, and give suggestions according to the sorting. The current civilized driving dimension has the lowest score, and it is necessary to recommend the fleet / driver to strengthen the civilized driving behavior training to promote civilized driving. Economic behavior and driving control are second, among which the energy consumption score is the lowest, and the vehicle speed and motor control scores are low. It is necessary to recommend the fleet / driver to increase vehicle driving behavior training, avoid excessive speed changes, maintain a stable vehicle speed so that the motor works in the high-efficiency range, and reduce operating energy consumption. Work status is third. If the attendance time is not full, the team / driver needs to communicate with the management staff about the attendance. Safety behavior is fourth. The team / driver needs to be advised to strengthen safety shutdown and avoid playing with mobile phones and smoking while driving (behaviors that occur more frequently). The cooperation degree is full marks, no suggestions are needed, and the team / driver is encouraged to continue to maintain it.

[0132] For example, set the corresponding suggestion template for each dimension, and only need to match it when displaying. For example: it is recommended that the fleet / driver increase the training of certain behavior. When the economic dimension parameter is low, it is recommended that the fleet / driver increase the training of vehicle driving energy-saving behavior.

[0133] S704: Send improvement suggestion information of the target dimension to the user equipment.

[0134] This allows drivers and their management organizations to review improvement suggestion information in a timely manner.

[0135] In summary, in this embodiment, the target driving behavior evaluation parameters of the target vehicle are calculated based on the driving behavior evaluation parameters of multiple dimensions; the driving behavior evaluation parameters of multiple dimensions are sorted; based on the sorted driving behavior evaluation parameters of each dimension, the preset suggestion templates of multiple dimensions are used to determine the improvement suggestion information of the target dimension in each dimension; and the improvement suggestion information of the target dimension is sent to the user device. Thus, the improvement suggestion information of the target dimension is accurately generated.

[0136] On the basis of the above embodiment, in another embodiment of the present application, not only the target driving suggestion information is sent to the user device, but also the target driving behavior evaluation parameters, driving related data and other data are sent to the user device. So that the above data can be viewed in real time on the user device. It is also possible to collect statistics on driving data and target driving behavior evaluation parameters in multiple historical cycles, and rank multiple drivers, so that the data display is more intuitive.

[0137] The following is a description of the driving behavior analysis device, equipment, storage medium, etc. provided in this application for execution. The specific implementation process and technical effects are described above and will not be repeated below.

[0138] Figure 8 Schematic diagram of a driving behavior analysis device provided in an embodiment of the present application. Figure 8 As shown, the device comprises: The receiving module 801 is used to receive the vehicle driving data of the target vehicle in a preset historical time period uploaded by the user equipment.

[0139] The extraction module 802 is used to extract features from the vehicle driving data to obtain a plurality of driving feature data.

[0140] The classification module 803 is used to classify the multiple driving characteristic data to obtain the driving characteristic data corresponding to multiple dimensions.

[0141] The evaluation module 804 is used to evaluate the driving behavior of the target vehicle in each dimension according to the driving characteristic data corresponding to each dimension, and obtain the driving behavior evaluation parameters of the target vehicle in each dimension.

[0142] The sending module 805 is used to send target driving suggestion information to the user equipment according to the driving behavior evaluation parameters in multiple dimensions.

[0143] Furthermore, the extraction module 802 is specifically used for multiple driving characteristic data including: motion characteristic data, driving behavior characteristic data, interval characteristic data, drive motor characteristic data, and alarm characteristic data; performing a first feature extraction on the vehicle driving data to obtain motion characteristic data; performing a second feature extraction on the vehicle driving data to obtain driving behavior characteristic data; performing a third feature extraction on the vehicle driving data to obtain interval characteristic data; performing a fourth feature extraction on the vehicle driving data to obtain drive motor characteristic data and alarm characteristic data.

[0144] Furthermore, the extraction module 802 is specifically used for motion feature data including: speed feature data, acceleration feature data, and deceleration feature data; speed feature extraction is performed based on the vehicle driving data to obtain the speed feature data and speeding feature data of the target vehicle; wherein, the speed feature data includes: speed feature data and speeding feature data; acceleration feature extraction is performed based on the vehicle driving data to obtain the number of sudden accelerations and acceleration of the target vehicle; wherein, the acceleration feature data includes: the number of sudden accelerations and acceleration; deceleration feature extraction is performed based on the vehicle driving data to obtain the number of sudden decelerations, deceleration, number of sudden decelerations, number of high-speed continuous brakings, number of emergency stops and braking duration of the target vehicle; wherein, the deceleration feature data includes: the number of sudden decelerations, deceleration, number of sudden decelerations, number of high-speed continuous brakings, number of emergency stops and braking duration.

[0145] Further, the extraction module 802 is specifically used for driving behavior characteristic data including: energy consumption behavior characteristic data, uncivilized behavior characteristic data, and dangerous behavior characteristic data; energy consumption characteristics are extracted according to the vehicle driving data to obtain the air conditioning usage time, low battery driving times, parking accelerator times, and parking idling times; wherein the energy consumption behavior characteristic data include: air conditioning usage time, low battery driving times, parking accelerator times, and parking idling times; uncivilized characteristics are extracted according to the vehicle driving data to obtain the number of frequent lane changes, the number of lane changes without turning on the lights, the number of turns without stopping, and the number of turns without turning on the lights; the uncivilized behavior characteristic data include: the number of frequent lane changes, the number of lane changes without turning on the lights, the number of turns without stopping, and the number of turns without turning on the lights; dangerous characteristics are extracted according to the vehicle driving data to obtain the number of sharp turns, fatigue driving, and neutral coasting times of the target vehicle; wherein the dangerous behavior characteristic data include: the number of sharp turns, fatigue driving, and neutral coasting times.

[0146] Furthermore, the extraction module 802 is specifically used to calculate the vehicle start-up time, total vehicle power consumption, total vehicle interval mileage and kinetic energy recovery power of the target vehicle based on the vehicle driving data; wherein the interval characteristic data includes: vehicle start-up time, total vehicle power consumption, total vehicle interval mileage and kinetic energy recovery power.

[0147] Furthermore, the extraction module 802 is specifically used to calculate the economic speed ratio of the drive motor of the target vehicle as the drive motor characteristic data based on the vehicle driving data; and extract the number of ADAS alarms and the number of DMS alarms from the vehicle driving data as the alarm characteristic data.

[0148] Furthermore, the classification module 803 is specifically used for driving characteristic data corresponding to multiple dimensions, including: economic dimension characteristic data, safety dimension characteristic data, control dimension characteristic data, civilization dimension characteristic data, working status dimension characteristic data, and cooperation dimension data, wherein the economic dimension characteristic data is used to characterize the energy consumption of the target vehicle, the safety dimension characteristic data is used to characterize the driving safety of the target vehicle, the control dimension characteristic data is used to characterize the vehicle control status of the target vehicle, the civilization dimension characteristic data is used to characterize whether the driving behavior of the target vehicle complies with the preset civilized driving specifications, the working status dimension characteristic data is used to characterize the working status of the driver of the target vehicle, and the cooperation dimension data is used to characterize whether the driver of the target vehicle adjusts the driving behavior with reference to driving suggestions; multiple driving characteristic data are classified to obtain economic dimension characteristic data, safety dimension characteristic data, control dimension characteristic data, civilization dimension characteristic data, working status dimension characteristic data, and cooperation dimension data.

[0149] Furthermore, the evaluation module 804 is specifically used to calculate the evaluation parameters of each driving characteristic data corresponding to each dimension respectively, and obtain at least one evaluation parameter of each dimension; according to the at least one evaluation parameter of each dimension, calculate the driving behavior evaluation parameter of each dimension.

[0150] Furthermore, the sending module 805 is specifically used to calculate the target driving behavior evaluation parameters of the target vehicle based on the driving behavior evaluation parameters of multiple dimensions; sort the driving behavior evaluation parameters of multiple dimensions; based on the sorted driving behavior evaluation parameters of each dimension, use the preset suggestion templates of multiple dimensions to determine the improvement suggestion information of the target dimension in each dimension; and send the improvement suggestion information of the target dimension to the user device.

[0151] Fig. 9 A schematic diagram of an Internet of Vehicles server provided in an embodiment of the present application, which Internet of Vehicles server may be a device with computing and processing capabilities.

[0152] The Internet of Vehicles server includes: a processor 901 and a storage medium 902. The processor 901 and the storage medium 902 are connected via a bus.

[0153] The storage medium 902 is used to store programs, and the processor 901 calls the programs stored in the storage medium 902 to execute the above method embodiment. The specific implementation method and technical effect are similar and will not be repeated here.

[0154] Optionally, the present invention also provides a storage medium, including a program, which is used to execute the above-mentioned method embodiment when executed by a processor. In the several embodiments provided by the present invention, it should be understood that the disclosed devices and methods can be implemented in other ways. For example, the device embodiments described above are merely schematic. For example, the division of the units is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0155] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0156] In addition, each functional unit in each embodiment of the present invention may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of hardware plus software functional units.

[0157] The above-mentioned integrated unit implemented in the form of a software functional unit can be stored in a storage medium. The above-mentioned software functional unit is stored in a storage medium, including a number of instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) or a processor (English: processor) to perform some steps of the method described in each embodiment of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (English: Read-Only Memory, abbreviated: ROM), random access memory (English: Random Access Memory, abbreviated: RAM), disk or optical disk and other media that can store program codes.

Claims

1. A driving behavior analysis method, characterized in that: The method comprises: Receiving vehicle driving data of a target vehicle in a preset historical time period uploaded by a user device; Extracting features from the vehicle driving data to obtain a plurality of driving feature data; Classifying the plurality of driving characteristic data to obtain driving characteristic data corresponding to a plurality of dimensions; According to the driving characteristic data corresponding to each dimension, the driving behavior of the target vehicle is evaluated in each dimension to obtain the driving behavior evaluation parameters of the target vehicle in each dimension; According to the driving behavior evaluation parameters in the multiple dimensions, target driving suggestion information is sent to the user equipment.

2. The method according to claim 1, characterized in that The plurality of driving characteristic data include: motion characteristic data, driving behavior characteristic data, interval characteristic data, drive motor characteristic data, and alarm characteristic data; The feature extraction of the vehicle driving data is performed to obtain a plurality of driving feature data, including: Performing a first feature extraction on the vehicle driving data to obtain the motion feature data; Performing a second feature extraction on the vehicle driving data to obtain the driving behavior feature data; Performing a third feature extraction on the vehicle driving data to obtain the interval feature data; A fourth feature extraction is performed on the vehicle driving data to obtain the drive motor feature data and the alarm feature data.

3. The method according to claim 2, characterized in that The motion characteristic data includes: speed characteristic data, acceleration characteristic data, and deceleration characteristic data; The first feature extraction is performed on the vehicle driving data to obtain the motion feature data, including: Extracting speed characteristics according to the vehicle driving data to obtain vehicle speed characteristic data and speeding characteristic data of the target vehicle; wherein the speed characteristic data includes: the vehicle speed characteristic data and the speeding characteristic data; Extracting acceleration features according to the vehicle driving data to obtain the number of sudden accelerations and the acceleration of the target vehicle; wherein the acceleration feature data includes: the number of sudden accelerations and the acceleration; The deceleration characteristics are extracted according to the vehicle driving data to obtain the number of sudden decelerations, deceleration, number of sudden decelerations, number of high-speed continuous brakings, number of emergency stops and braking duration of the target vehicle; wherein the deceleration characteristic data includes: the number of sudden decelerations, the deceleration, the number of sudden decelerations, the number of high-speed continuous brakings, the number of emergency stops and the braking duration.

4. The method according to claim 2, characterized in that: The driving behavior characteristic data includes: energy consumption behavior characteristic data, uncivilized behavior characteristic data, and dangerous behavior characteristic data; The extracting the second feature of the vehicle driving data to obtain the driving behavior feature data includes: Energy consumption characteristics are extracted according to the vehicle driving data to obtain the air conditioning use time, low battery driving times, parking accelerator pedal times, and parking idling times; wherein the energy consumption behavior characteristic data includes: the air conditioning use time, low battery driving times, parking accelerator pedal times, and parking idling times; Uncivilized behavior features are extracted based on the vehicle driving data to obtain the number of frequent lane changes, the number of lane changes without turning on the lights, the number of turns without stopping, and the number of turns without turning on the lights; the uncivilized behavior feature data includes: the number of frequent lane changes, the number of lane changes without turning on the lights, the number of turns without stopping, and the number of turns without turning on the lights; Dangerous features are extracted based on the vehicle driving data to obtain the number of sharp turns, the number of fatigue driving, and the number of neutral coasting of the target vehicle; wherein the dangerous behavior feature data includes: the number of sharp turns, the number of fatigue driving, and the number of neutral coasting.

5. The method according to claim 2, characterized in that: The extracting the third feature from the vehicle driving data to obtain the interval feature data includes: According to the vehicle driving data, the vehicle startup time, the total vehicle power consumption, the total vehicle interval mileage and the kinetic energy recovery power of the target vehicle are calculated; wherein the interval characteristic data includes: the vehicle startup time, the total vehicle power consumption, the total vehicle interval mileage and the kinetic energy recovery power.

6. The method according to claim 2, characterized in that The fourth feature extraction is performed on the vehicle driving data to obtain the driving motor feature data and the alarm feature data, including: Calculating the economic speed ratio of the drive motor of the target vehicle as the drive motor characteristic data according to the vehicle driving data; The number of advanced driving assistance system ADAS alarms and the number of driver monitoring system DMS alarms are extracted from the vehicle driving data as the alarm feature data.

7. The method according to claim 1, characterized in that The driving characteristic data corresponding to the multiple dimensions include: economic dimension characteristic data, safety dimension characteristic data, control dimension characteristic data, civilization dimension characteristic data, working state dimension characteristic data, and cooperation degree dimension data, wherein the economic dimension characteristic data is used to characterize the energy consumption of the target vehicle, the safety dimension characteristic data is used to characterize the driving safety of the target vehicle, the control dimension characteristic data is used to characterize the vehicle control state of the target vehicle, the civilization dimension characteristic data is used to characterize whether the driving behavior of the target vehicle complies with the preset civilized driving specifications, the working state dimension characteristic data is used to characterize the working state of the driver of the target vehicle, and the cooperation degree dimension data is used to characterize whether the driver of the target vehicle adjusts the driving behavior with reference to the driving suggestions; The classifying the plurality of driving characteristic data to obtain driving characteristic data corresponding to a plurality of dimensions includes: The multiple driving characteristic data are classified to obtain the economic dimension characteristic data, the safety dimension characteristic data, the control dimension characteristic data, the civilization dimension characteristic data, the working status dimension characteristic data, and the cooperation dimension data.

8. The method according to claim 1, characterized in that The step of performing driving behavior evaluation on the target vehicle in each dimension according to the driving characteristic data corresponding to each dimension to obtain a driving behavior evaluation parameter of the target vehicle in each dimension includes: Calculating evaluation parameters of each driving characteristic data corresponding to each dimension respectively to obtain at least one evaluation parameter of each dimension; According to the at least one evaluation parameter of each dimension, a driving behavior evaluation parameter of each dimension is calculated.

9. The method according to claim 1, characterized in that: The sending target driving suggestion information to the user equipment according to the driving behavior evaluation parameters of the multiple dimensions includes: Calculating a target driving behavior evaluation parameter of the target vehicle according to the driving behavior evaluation parameters of the multiple dimensions; sorting the driving behavior evaluation parameters of the multiple dimensions; According to the sorted driving behavior evaluation parameters of each dimension, using the preset suggestion templates of the multiple dimensions, determining the improvement suggestion information of the target dimension in each dimension; Send improvement suggestion information of the target dimension to the user equipment.

10. A vehicle networking server, characterized in that: include: A processor and a storage medium, wherein the processor and the storage medium are connected to each other via a bus communication, the storage medium stores program instructions executable by the processor, and the processor calls the program stored in the storage medium to execute the steps of the driving behavior analysis method as described in any one of claims 1 to 9.

Images