Driving behavior analysis method and device, electronic equipment and storage medium

Abstract

The embodiment of the invention provides a driving behavior analysis method and device, electronic equipment and a storage medium, and relates to the technical field of data analysis, and the method comprises the steps: obtaining a first vehicle signal corresponding to a vehicle in a first vehicle travel; performing indexing processing on the first vehicle signal to obtain a corresponding first driving index; a configuration table for the first driving index is obtained, driving behavior analysis is conducted on a driver according to the configuration table and the first driving index, driving style data corresponding to the driver are obtained, and therefore the driving style data of the driver are obtained by collecting vehicle signals corresponding to a vehicle. Vehicle signals are converted into driving indexes capable of being used for analyzing the driving style of the driver, then analysis and calculation are conducted in combination with a corresponding configuration table, and style evaluation of the driver is achieved.

Description

Technical Field

[0001] The present invention relates to the field of data analysis technology, and in particular to a driving behavior analysis method, a driving behavior analysis device, an electronic device, and a computer-readable storage medium. Background Art

[0002] Aggressive driving behaviors, such as sudden acceleration, braking, and sharp turns, can reduce vehicle stability and increase the risk of loss of control. Aggressive driving also puts significant stress and wear on various vehicle components. Rapid acceleration and deceleration during aggressive driving can significantly increase fuel consumption. For traffic management, aggressive driving can disrupt normal traffic flow, leading to unstable traffic flow and increasing the probability of traffic accidents. Collecting and analyzing data on driving intensity and understanding drivers' driving habits and needs can effectively inform vehicle manufacturers' R&D and improvements. For example, based on the vehicle's performance during aggressive driving, the suspension, braking, and powertrain systems can be optimized to improve vehicle handling and safety. Summary of the Invention

[0003] The embodiments of the present invention provide a driving behavior analysis method, device, electronic device, and computer-readable storage medium to solve or partially solve the problem of being unable to accurately analyze a user's driving behavior.

[0004] An embodiment of the present invention discloses a driving behavior analysis method, comprising:

[0005] Acquire a first vehicle signal corresponding to the vehicle in a first vehicle trip;

[0006] performing indexing processing on the first vehicle signal to obtain a corresponding first driving index;

[0007] A configuration table for the first driving index is obtained, and a driving behavior analysis of the driver is performed based on the configuration table and the first driving index to obtain driving style data corresponding to the driver.

[0008] The embodiment of the present invention further discloses a driving behavior analysis device, comprising:

[0009] A signal acquisition module, configured to acquire a first vehicle signal corresponding to the vehicle during a first vehicle trip;

[0010] an index processing module, configured to perform index processing on the first vehicle signal to obtain a corresponding first driving index;

[0011] The analysis module is configured to obtain a configuration table for the first driving index, and perform a driving behavior analysis on the driver based on the configuration table and the first driving index to obtain driving style data corresponding to the driver.

[0012] An embodiment of the present invention further discloses an electronic device, including:

[0013] one or more processors; and

[0014] One or more machine-readable media having instructions stored thereon, when executed by the one or more processors, enable the electronic device to perform the method according to the embodiment of the present invention.

[0015] An embodiment of the present invention further discloses a computer-readable storage medium having instructions stored thereon. When executed by one or more processors, the processors are enabled to execute the method according to the embodiment of the present invention.

[0016] The embodiments of the present invention include the following advantages:

[0017] In an embodiment of the present invention, a first vehicle signal corresponding to a vehicle during a first vehicle trip is acquired, the first vehicle signal is then indexed to obtain a corresponding first driving index, a configuration table for the first driving index is then acquired, and the driver's driving behavior is analyzed based on the configuration table and the first driving index to obtain driving style data corresponding to the driver. Thus, by collecting the vehicle signal corresponding to the vehicle, the vehicle signal is converted into a driving index that can be used to analyze the driver's driving style. Then, analysis and calculation are performed in combination with the corresponding configuration table to implement a driver style assessment. Furthermore, based on the assessment results, the driver's driving style can be analyzed to provide the driver with more personalized driving content and enhance the driver's driving experience. Furthermore, the assessment results can provide a corresponding reference for vehicle manufacturers' research and development and improvements to improve the vehicle's controllability and safety. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] Figure 1 is a flowchart of a driving behavior analysis method provided in an embodiment of the present invention;

[0019] Figure 2 is a schematic diagram of a driving style evaluation process provided in an embodiment of the present invention;

[0020] Figure 3 1 is a flow chart of data analysis provided in an embodiment of the present invention;

[0021] Figure 4 This is a structural block diagram of a driving behavior analysis device provided in an embodiment of the present invention. DETAILED DESCRIPTION

[0022] In order to make the above-mentioned objects, features and advantages of the present invention more obvious and easy to understand, the present invention is further described in detail below with reference to the accompanying drawings and specific embodiments.

[0023] As an example, for drivers, vehicle manufacturers can provide more personalized driving content based on the driver's driving style to enhance the driver's driving experience; for vehicle manufacturers, based on the driving styles of different drivers, they can provide corresponding references for vehicle research and development and improvement, such as optimizing the vehicle's suspension system, braking system and power system, etc., to improve the vehicle's handling and safety.

[0024] In this regard, in the present invention, a first vehicle signal corresponding to the vehicle in a first vehicle trip is obtained, and then the first vehicle signal is indexed to obtain a corresponding first driving index. Then, a configuration table for the first driving index is obtained, and the driver's driving behavior is analyzed based on the configuration table and the first driving index to obtain driving style data corresponding to the driver. Thus, by collecting the vehicle signal corresponding to the vehicle, the vehicle signal is converted into a driving index that can be used to analyze the driver's driving style, and then analyzed and calculated in combination with the corresponding configuration table to achieve driver style evaluation. Then, based on the evaluation results, the driver's driving style can be analyzed to provide the driver with more personalized driving content and enhance the driver's driving experience. In addition, the evaluation results can provide corresponding references for vehicle manufacturers' research and development and improvements to improve the vehicle's controllability and safety.

[0025] Reference Figure 1 , shows a flowchart of a driving behavior analysis method provided by an embodiment of the present invention, which may specifically include the following steps:

[0026] Step 101, obtaining a first vehicle signal corresponding to a vehicle in a first vehicle trip;

[0027] During the driving process of the vehicle, the vehicle can obtain vehicle signals corresponding to the driver's control of the vehicle. The vehicle signals can be the driving dynamics parameters of the vehicle during the driving process, such as vehicle speed information (used to reflect the real-time speed of the vehicle), brake pedal status (used to indicate whether the driver has stepped on the brake pedal), maximum longitudinal deceleration within 1 second (used to reflect the severity of vehicle braking or deceleration), maximum longitudinal acceleration within 1 second (used to reflect the severity of vehicle acceleration), maximum lateral deceleration within 1 second (used to reflect the intensity of vehicle lateral deceleration (such as cornering braking)), maximum lateral acceleration within 1 second (used to reflect the severity of vehicle steering or lateral movement), actual accelerator pedal position (used to indicate the driver's control over the accelerator pedal) and collision time (key time node for triggering vehicle collision), etc., so as to analyze the driver's driving style based on the obtained vehicle signals.

[0028] For a vehicle, it can be equipped with a cockpit system, an electric drive control system, and an intelligent driving system. During the analysis of the driver's driving style, the driver can enter a corresponding user identity into the cockpit system (e.g., logging into a corresponding user account in the system). After obtaining the driver's corresponding user identity, the cockpit system can upload the user identity to the cloud. At the same time, during the vehicle's driving process, the electric drive control system can obtain corresponding vehicle signals (e.g., vehicle speed information, brake pedal status, maximum longitudinal deceleration within 1 second, maximum longitudinal acceleration within 1 second, maximum lateral deceleration within 1 second, maximum lateral acceleration within 1 second, actual accelerator pedal position, etc.), and the intelligent driving system can obtain the positional relationship between the vehicle and other vehicles (e.g., the speed of the preceding vehicle, the distance between the preceding vehicle and the preceding vehicle, lane departure signs), etc. The electric drive control system and the intelligent driving system can then report the collected relevant signals to the cockpit system, which can then upload them to the cloud in a unified manner so that the cloud can analyze the driver's driving style based on the data reported by the vehicle. Optionally, the cloud can be a cloud server, etc., and the present invention is not limited to this.

[0029] The first vehicle trip can be a series of dynamic events and state changes involved in the vehicle's driving process, covering the period from vehicle power-up to power-down. During some vehicle trips, the vehicle can collect vehicle signals corresponding to the driver's driving process to analyze the driver's driving style during the trip. Optionally, the first vehicle trip can be the driver's current driving process or the driver's past driving process, which is not limited in the present invention.

[0030] Step 102: performing indexing processing on the first vehicle signal to obtain a corresponding first driving index;

[0031] After collecting the first vehicle signal corresponding to the vehicle's driving process, the vehicle can upload the first vehicle signal to the cloud, and the cloud will perform index processing on the first vehicle signal to obtain the corresponding first driving index. By performing index processing on the vehicle signal, an evaluation index corresponding to the driving behavior during driving (i.e., the driving index) is obtained, so as to accurately analyze the driver's driving style based on different driving indicators.

[0032] It should be noted that indexation processing refers to converting vehicle signals involved in the vehicle driving process into discrete indicators or statistical features with clear meanings through preset indexation conditions (such as preset conditions, algorithms or threshold judgments, etc.) to more intuitively evaluate the driver's driving behavior during the vehicle journey, that is, the process of converting high-dimensional, continuous sensor data into low-dimensional, interpretable statistical indicators, so that the driver's driving style can be accurately analyzed based on the various driving indicators after indexation processing.

[0033] Driving indicators can be standardized parameters generated by quantifying, statistically analyzing, or logically analyzing vehicle signals to assess driving behavior, vehicle status, or driving safety. These indicators can include speeding, braking, sudden deceleration, extremely rapid deceleration, collision information, and ride comfort test results.

[0034] Optionally, the number of speeding times can be the process in which the vehicle changes from being below a first speed threshold to exceeding a second speed threshold during driving. When the vehicle is triggered once within a certain time period (such as 1 minute, etc.), a count is triggered; the number of braking times can be the number of times the brake pedal state changes from not triggered to triggered when the vehicle speed is greater than a preset speed threshold; the number of sudden deceleration times and the number of extremely urgent deceleration times are the number of times the driver triggers sudden deceleration, and the triggering conditions corresponding to the two can be different. The triggering conditions corresponding to the number of extremely urgent deceleration times are more stringent than those for the number of sudden deceleration times; the collision information can be the number of times the collision time is lower than a preset threshold, and the collision time can be the collision duration between the vehicle and the vehicle in front. When the collision time is less than the preset threshold, the vehicle and the vehicle in front are The greater the probability of a vehicle collision, the greater the probability of a vehicle collision. Based on this, during the vehicle's driving process, the collision time between the vehicle and the vehicle in front is calculated by obtaining information such as the vehicle's current speed, the speed of the vehicle in front, and the target longitudinal distance of the lane. When the collision time is lower than the preset threshold, it is counted once. By counting the collision information, the number of near collisions between the vehicle and the vehicle in front in one trip can be determined; the smoothness test result can be a measure of the vehicle's stability during driving. By analyzing the vehicle signals reported by the vehicle, such as the maximum longitudinal deceleration within 1s, the maximum longitudinal acceleration within 1s, the maximum lateral deceleration within 1s, and the maximum lateral acceleration within 1s, the vehicle can be tested for lateral and longitudinal smoothness to determine the smoothness of the vehicle during driving.

[0035] In some feasible implementations, the cloud can first obtain various indexation conditions corresponding to the first vehicle signals reported by the vehicle to the cloud, and then perform indexation processing on the first vehicle signals according to the indexation conditions to obtain corresponding first driving indicators. The first driving indicators can then be used to analyze the driver's driving behavior and determine the driver's driving style. Optionally, the cloud can be a cloud server.

[0036] Among them, the indexation conditions include a first trigger condition for vehicle speed information, a second trigger condition for brake pedal status, a third trigger condition and a fourth trigger condition for maximum longitudinal deceleration within 1s, a fifth trigger condition for the actual position of the accelerator pedal, a sixth trigger condition for collision time, and at least one of the seventh trigger conditions of maximum longitudinal deceleration within 1s, maximum longitudinal acceleration within 1s, maximum lateral deceleration within 1s, and maximum lateral acceleration within 1s.

[0037] Performing indexing processing on the first vehicle signal according to the indexing condition to obtain a corresponding first driving index includes at least one of the following:

[0038] Processing the vehicle speed information according to the first trigger condition to obtain the number of speeding times;

[0039] Processing the brake pedal state according to the second trigger condition to obtain the number of braking times;

[0040] Processing the maximum longitudinal deceleration within 1 second according to the third trigger condition and / or the actual position of the accelerator pedal according to the fifth trigger condition to obtain the number of rapid decelerations;

[0041] The maximum longitudinal deceleration within 1 second is processed according to the fourth trigger condition to obtain the number of urgent decelerations;

[0042] Processing the collision time according to the sixth trigger condition to obtain collision information;

[0043] According to the seventh trigger condition, the maximum longitudinal deceleration within 1 second, the maximum longitudinal acceleration within 1 second, the maximum lateral deceleration within 1 second, and the maximum lateral acceleration within 1 second are processed to obtain a smoothness test result.

[0044] In some feasible examples, for the triggering process of the number of speeding times, the triggering conditions may at least include:

[0045] A. The vehicle speed changes from less than 120 km / h (TBD) to more than 120 km / h (TBD) (only triggered once within 1 minute);

[0046] B. The vehicle speed changes from less than 130 km / h (TBD) to more than 130 km / h (TBD) (only triggered once within 1 minute);

[0047] C. The vehicle speed changes from less than 140 km / h (TBD) to more than 140 km / h (TBD) (only triggered once within 1 minute);

[0048] D. The current vehicle speed exceeds 20% of the average speed in the previous minute (TBD) (only triggered once in 1 minute);

[0049] E. The current vehicle speed exceeds 30% of the average speed in the previous minute (TBD) (only triggered once in 1 minute);

[0050] F. The current vehicle speed exceeds 40% of the average speed in the previous minute (TBD) (only triggered once in 1 minute);

[0051] G. Speeding (vehicle speed is higher than 120km / h (TBD) or the vehicle speed exceeds 20% of the average speed in the previous minute (TBD)), etc.

[0052] When the vehicle's speed meets one of the above conditions, it can be determined that the driver has performed a speeding behavior, and the number of speeding times is increased by 1.

[0053] For the number of brakes, the cloud can use the brake pedal status reported by the vehicle to calculate the corresponding number of brakes. When the vehicle speed VCU_VehicleSpeed ​​is higher than 20km / h (TBD), if the brake pedal status VCU_brakePedalState jumps from 0x0 to 0x1, the number of brakes is increased by 1.

[0054] For the number of sudden decelerations, the cloud can use the maximum longitudinal deceleration within 1s reported by the cockpit to calculate the number of sudden decelerations. When the maximum longitudinal deceleration VCU_MinLongAcceleration within 1s is lower than -3M / s, 2 to greater than -3M / s 2 , the number of rapid decelerations increases by 1.

[0055] For the number of urgent decelerations, the cloud can use the maximum longitudinal deceleration within 1s reported by the vehicle to calculate the number of urgent decelerations. When the maximum longitudinal deceleration VCU_MinLongAcceleration within 1s is lower than -6M / s, 2 When the speed is greater than -6M / s2, the number of emergency decelerations is increased by 1.

[0056] Correspondingly, the number of sudden decelerations can also correspond to the number of times the brake pedal is deeply depressed. The cloud can use the actual position of the accelerator pedal reported by the vehicle to calculate the number of times the brake pedal is deeply depressed (i.e. the number of sudden decelerations). When the actual position of the accelerator pedal is valid, VCU_AccPedalActualPositionValid = 0x1: Valid, and the actual position of the accelerator pedal VCU_AccPedalActualPosition changes from less than 50% to greater than 50% (TBD), the number of times the brake pedal is deeply depressed is increased by 1.

[0057] For collision information, the cloud can use the vehicle's reported speed, the target vehicle's speed, and the target longitudinal distance in the own lane to calculate the corresponding collision time, and then count the number of times the collision time is below the threshold. Specifically, collision time = target longitudinal distance in the own lane / (vehicle speed - target vehicle's speed). Then, combined with the vehicle speed, it is determined whether the collision time is less than the preset threshold. The relationship between vehicle speed and collision time is shown in Table 1 below:

[0058] Collision time (s) Current vehicle speed (km / h) T1 V1 T2 V2 …… ……

[0059] Table 1

[0060] When the collision time is less than a preset threshold, the number of times the collision time is less than the preset threshold can be increased by 1, so that the number of near collisions between the vehicle and the preceding vehicle in a trip can be determined by counting the collision information.

[0061] For ride comfort testing, the cloud can use the maximum longitudinal acceleration within 1 second, the maximum longitudinal deceleration within 1 second, the maximum lateral acceleration within 1 second, and the maximum lateral deceleration within 1 second reported by the vehicle to perform ride comfort testing. The corresponding trigger conditions may include:

[0062] A. Within 5 minutes and 1 second, the maximum longitudinal acceleration root mean square value is greater than 0.5M / s 2 ;

[0063] B. Within 5 minutes, the maximum longitudinal deceleration root mean square value within 1 second is greater than 0.5M / s 2 ;

[0064] C. Within 5 minutes, the maximum lateral acceleration within 1 second is greater than 0.5M / s 2 ;

[0065] D. Within 5 minutes, the root mean square value of the maximum lateral deceleration within 1 second is greater than 0.5M / s 2 .

[0066] If the trigger conditions A|B are met and the longitudinal smoothness test fails, the count is increased by 1; if the trigger conditions C|D are met and the lateral smoothness test fails, the count is increased by 1, thereby obtaining the corresponding smoothness test result.

[0067] Through the above process, vehicle signals can be indexed and processed to obtain corresponding driving indicators, such as the number of speeding, braking, sudden deceleration, extremely rapid deceleration, collision information, and ride comfort test results. A corresponding driving indicator statistical table is then constructed based on the driving indicators. The driving indicator statistical table can include information such as vehicle ID, user ID, trip start time, and driving duration to more accurately distinguish driving indicators corresponding to different trips. The driving indicator statistical table can include the field name, field type, and field description corresponding to each driving indicator. The field name identifies the driving indicator; the field type describes the data nature, format, and value range corresponding to the driving indicator, and can be used to define data storage methods, processing rules, and allowed operations; and the field description describes the actual information corresponding to the driving indicator.

[0068] Optionally, the driving index statistics table may be as shown in Table 2 below:

[0069]

[0070]

[0071]

[0072]

[0073]

[0074] Table 2

[0075] Step 103 : Obtain a configuration table for the first driving index, and perform a driving behavior analysis on the driver based on the configuration table and the first driving index to obtain driving style data corresponding to the driver.

[0076] After obtaining the corresponding driving indicators, each driving indicator can be further counted, and the driver's driving behavior can be analyzed in combination with the corresponding configuration table to obtain the driver's corresponding driving style data. By collecting the vehicle signal corresponding to the vehicle, the vehicle signal is converted into a driving indicator that can be used to analyze the driver's driving style, and then analyzed and calculated in combination with the corresponding configuration table to achieve the driver's style evaluation. Based on the evaluation results, it is convenient to analyze the driver's driving style, so as to provide the driver with more personalized driving content and improve the driver's driving experience. The evaluation results can also provide corresponding references for the research and development and improvement of vehicle manufacturers to improve the vehicle's controllability and safety.

[0077] In some feasible implementations, the configuration table may be a form for setting weight coefficients for different driving indicators, which includes at least a driving indicator upper limit configuration table and a working condition coefficient configuration table, wherein the driving indicator upper limit configuration table may include upper limit values ​​corresponding to different driving indicators, and the working condition coefficient configuration table may include indicator weights corresponding to different driving indicators, and the two respectively correspond to the score proportion of driving indicators and the working condition proportion in the process of evaluating the driver's driving style. The evaluation process of the driving style data may be to evaluate the data accumulated for a preset time in the driving indicator statistics table to obtain the driver's driving score for the preset time.

[0078] In a specific implementation, the upper limit value corresponding to the first driving indicator can be obtained from a driving indicator upper limit configuration table, and the indicator weight corresponding to the first driving indicator can be obtained from a working condition coefficient configuration table. The corresponding driving time of the vehicle can then be obtained. The first driving indicator is then normalized based on the driving time to obtain a second driving indicator. The first driving indicator is a description of the driver's actual driving behavior, and the second driving indicator is a description of the driving behavior performed within a preset time. An evaluation is then performed based on the driving time, the upper limit value, the indicator weight, and the second driving indicator to obtain a driving indicator score corresponding to the second driving indicator. Finally, based on the driving time, the first driving indicator, the second driving indicator, and the driving indicator score, the driver's driving style data is constructed. After obtaining the corresponding driving indicators, analysis and calculation can be performed in conjunction with the corresponding configuration table to evaluate the driver's driving style. The evaluation results can then be used to analyze the driver's driving style, thereby providing the driver with more personalized driving content and enhancing the driver's driving experience. The evaluation results can also provide a reference for vehicle manufacturers' research and development and improvements to improve vehicle controllability and safety.

[0079] Among them, the first driving indicator can be descriptive information of the driving behavior actually performed by the driver, such as the number of speeding, braking, sudden deceleration, extremely urgent deceleration, collision information, and smoothness test results that occurred during the driving process, while the second driving indicator can be the driving behavior performed by the driver within a preset time period converted according to the first driving indicator. For example, the preset time period can be 100 hours, and the second driving indicator can include the number of speeding, braking, sudden deceleration, extremely urgent deceleration, collision information, and smoothness test results converted within 100 hours. By converting the second driving indicator into driving behavior within the preset time period, the difference in the time dimension is eliminated, and the driver's driving style is evaluated based on the standard time period, thereby improving the accuracy and reliability of the analysis.

[0080] Optionally, for the standardized conversion process, different methods can be used for conversion according to different driving times. If the driving time is greater than or equal to the preset time, the first driving index and the driving time are used for calculation to obtain a second driving index corresponding to the first driving index; if the driving time is less than the preset time, the driving time and the preset time are used for calculation to obtain the actual time ratio of the driving time to the preset time, and then the actual time ratio, the index upper limit value and the first driving index are used for calculation to obtain the second driving index corresponding to the first driving index, so as to execute different index conversion strategies based on different driving times. When the driving time is sufficient, the conversion is performed based on the data corresponding to the driver's own driving behavior, which can effectively ensure the consistency of the converted driving index and the driving behavior; when the driving time is insufficient, the index conversion is performed in a "supplementary" manner to simulate the driver's driving behavior, thereby improving the flexibility of the conversion process.

[0081] In some feasible examples, assuming that the preset time is 100 hours, when the driver's driving time is greater than or equal to 100 hours, the conversion process of the driving index can be performed using the following formula:

[0082] Second driving index = first driving index ÷ actual total driving time (s) × 360,000s

[0083] For example, assuming the number of speeding violations is 30 and the actual total driving time is 100 hours, then:

[0084] Standard number of overspeeds in 100 hours = 30 ÷ 360,000 × 360,000 = 30

[0085] That is, the driver can exceed the speed limit by 30 times within 100 hours.

[0086] When the driver's driving time is less than 100 hours, it needs to be filled. The conversion process of driving index can be performed by the following formula:

[0087] Actual driving time ratio = (actual total driving time (s) ÷ 360,000s)

[0088] Filling duration ratio = 1 - actual duration ratio

[0089] Filling duration times = indicator maximum times × filling duration ratio × 50%

[0090] 100h standard times = actual times + filling time times

[0091] For example, assuming the number of speeding is 30 times, the actual total driving time is 30 hours, and the speeding limit is 50 times, then: the actual time accounts for 1 / 3, the filling time accounts for 2 / 3, and the number of filling time is 17 times (rounded to an integer), then the final standard speeding number for 100 hours can be 47 times.

[0092] Through the above-mentioned standardized processing, the differences in the time dimension can be eliminated, the driver's driving style can be evaluated based on the standard duration, and the accuracy and reliability of the analysis can be improved.

[0093] After obtaining the second driving index through the above process, the corresponding driving index score can be further calculated. Specifically, the quotient between the second driving index and the upper limit of the index can be calculated first, and then different processing processes can be performed according to the driving time. If the driving time is greater than or equal to the preset time, the smaller value is selected from the quotient and the preset threshold as the target value, and the target value and the index weight are used for evaluation to obtain the driving index score corresponding to the second driving index; if the driving time is less than the preset time, the quotient and the index weight are used for evaluation to obtain the driving index score corresponding to the second driving index. By calculating the corresponding driving index score, the driver's driving behavior is analyzed based on the driving index score to obtain the corresponding driving style data of the driver.

[0094] In some examples, assuming that the preset driving time is 100 hours, when the driver's driving time is greater than or equal to 100 hours, the driving index score of each driving index can be calculated using the following formula:

[0095] Driving index score = MIN (second driving index ÷ index number limit, 1) × 100 × index weight. When the driver's driving time is less than 100 hours, it can be calculated using the following formula:

[0096] Driving index score = standard number of times per 100 hours ÷ upper limit of index number × 100 × index weight

[0097] By calculating the corresponding driving index scores, the driver's driving behavior is analyzed based on the driving index scores to obtain the driver's corresponding driving style data.

[0098] After obtaining information such as driving time, the first driving indicator, the second driving indicator, and the driving indicator score, each driving indicator and its corresponding driving indicator score can be integrated to obtain the driver's corresponding driving style data. Optionally, the driving style data can be a driving style table. During the process of constructing the driving style table, the driver's corresponding user identity and vehicle identity can also be obtained. The user identity, vehicle identity, driving time, the first driving indicator, the second driving indicator, and the driving indicator score are then used to construct the driver's driving style table. By adding corresponding identifiers, the cloud can quickly locate the corresponding data, thereby improving the efficiency of driving behavior analysis.

[0099] In addition, the driving style table can also include trip records and partitions. Trip records can be used to record relevant information of the vehicle trip (such as trip start time, number of speeding, number of brakes, trip duration, etc.), while partitions can be used to distinguish data corresponding to different vehicle trips.

[0100] In one example, the driving style table formats the driving index and information related to the driving index according to the format of field name, field type, and field description, for example, as shown in Table 3 below:

[0101]

[0102]

[0103]

[0104] Table 3

[0105] Through the above-mentioned driving style table, the driver's driving style can be determined based on the scores corresponding to different driving behaviors recorded in the driving style table, and then the driver's driving style can be analyzed based on the evaluation results to provide the driver with more personalized driving content and improve the driver's driving experience. The evaluation results can also provide corresponding references for vehicle manufacturers' research and development and improvements to improve the vehicle's controllability and safety.

[0106] Alternatively, a second vehicle signal corresponding to a vehicle during a second vehicle trip can be obtained, where the first trip time point corresponding to the first vehicle trip is before the trip time point of the second vehicle trip. The second vehicle signal can then be indexed to obtain a corresponding third driving index. The first and third driving indexes can then be cumulatively calculated for the same driving index to obtain a corresponding fourth driving index. Furthermore, based on chronological order, driving indexes prior to a preset time period can be deleted from the fourth driving index to obtain a corresponding target driving index. The driver's driving behavior can then be analyzed based on the configuration table and the target driving index to obtain the driver's corresponding driving style data.

[0107] Among them, the driving style table contains the driver's driving style data. During a new vehicle trip of the driver, a new vehicle signal can be obtained. Based on the new vehicle signal, the cloud can perform driving behavior analysis again and merge the analysis results into the driving style table. In the merging process, the data corresponding to the previous vehicle trip in the driving style table can be read, and then accumulated with the incremental data calculated for this trip. After the cumulative calculation of the incremental number of times is completed, the corresponding failure calculation is performed, and then the result of the failure calculation, that is, the number of times corresponding to each driving indicator actually counted is converted into a standard number of preset time lengths, and scored to obtain the corresponding driving indicator score, and finally merged into the partition in the driving style table, thereby realizing the data update of the driving style table.

[0108] In one example, the incremental processing of the driving style table can be implemented by the following process:

[0109] For incremental calculations, the data for the driving metric statistics table at time T (where T is the current time) - 1 can be read first. Then, the data is grouped by vehicle ID and user ID, and the sum of the number of times each driving metric occurred on that day is calculated. Optionally, the number of times for each driving condition can be multiplied by a corresponding correction factor to improve data accuracy.

[0110] For data merging, the data in the T-2 partition of the driving style table itself can be read. Based on the vehicle and user IDs, as well as the incremental data, the calculated times for each driving metric are accumulated and summed. After the incremental times are accumulated, data invalidation is performed. Finally, after the incremental calculation and invalidation processing are complete, the actual counts for each driving metric are converted to a 100-hour standard times and scores. The merged data is then written to the T-1 (business date) partition of the driving style table itself.

[0111] For data aging, assume only 100 hours of actual driving time is retained. If the combined duration (total driving time) is greater than 100 hours, the trip_records field is read and a loop is initiated. First, the initial trip data is found. If duration minus the initial trip duration is ≥ 100 hours, the driving metrics for the initial trip are read and subtracted, while the trip information in the trip_records field is deleted. The loop continues to find the initial trip data in the remaining trips in trip_records and repeatedly checks for duration minus the initial trip duration ≥ 100 hours. This process continues until duration minus the initial trip duration is < 100 hours (ensuring that duration is closest to 100 hours and ≥ 100 hours). This concludes the aging process.

[0112] Through the above-mentioned processing of incremental calculation, data timeliness and data merging, the data update of the driving style table can be completed. By updating the driving style table, the driver's driving style can be accurately and effectively analyzed, so as to provide drivers with more personalized driving content based on their driving styles, improve the driver's driving experience, and provide corresponding references for vehicle manufacturers' research and development and improvements based on the evaluation results, so as to improve the vehicle's controllability and safety.

[0113] It should be noted that the embodiments of the present invention include but are not limited to the above examples. It is understandable that those skilled in the art can also make settings according to actual needs under the guidance of the ideas of the embodiments of the present invention, and the present invention does not limit this.

[0114] In an embodiment of the present invention, a first vehicle signal corresponding to a vehicle during a first vehicle trip is acquired, the first vehicle signal is then indexed to obtain a corresponding first driving index, a configuration table for the first driving index is then acquired, and the driver's driving behavior is analyzed based on the configuration table and the first driving index to obtain driving style data corresponding to the driver. Thus, by collecting the vehicle signal corresponding to the vehicle, the vehicle signal is converted into a driving index that can be used to analyze the driver's driving style. Then, analysis and calculation are performed in combination with the corresponding configuration table to implement a driver style assessment. Furthermore, based on the assessment results, the driver's driving style can be analyzed to provide the driver with more personalized driving content and enhance the driver's driving experience. Furthermore, the assessment results can provide a corresponding reference for vehicle manufacturers' research and development and improvements to improve the vehicle's controllability and safety.

[0115] In order to enable those skilled in the art to better understand the technical solutions in the embodiments of the present invention, the following examples are provided for illustrative purposes:

[0116] As an example, see Figure 2 , which shows a schematic diagram of a driving style evaluation process provided in an embodiment of the present invention. During the analysis of the driver's driving style, the driver can enter a corresponding user identity into the cockpit system (e.g., logging into a corresponding user account in the system). After obtaining the driver's corresponding user identity, the cockpit system can upload the user identity to the cloud. Meanwhile, during the vehicle's driving process, the electric drive control system can obtain corresponding vehicle signals (e.g., vehicle speed information, brake pedal status, maximum longitudinal deceleration within 1 second, maximum longitudinal acceleration within 1 second, maximum lateral deceleration within 1 second, maximum lateral acceleration within 1 second, actual accelerator pedal position, etc.), and the intelligent driving system can obtain the positional relationship between the vehicle and other vehicles (e.g., the speed of the preceding vehicle, the distance between the preceding vehicle and the preceding vehicle, lane departure signs), etc. The electric drive control system and the intelligent driving system can then report the collected relevant signals to the cockpit system, which can then upload them to the cloud in a unified manner, so that the cloud can analyze the driver's driving style based on the data reported by the vehicles. After the analysis is completed, the cloud can send the current driver's driving behavior score to the cockpit control system. Then, if the driver turns on the adaptive driving style, the cockpit control system can forward the current driver's driving behavior score and the adaptive driving style function switch status to the vehicle-side VCU. After the electric drive control system receives the corresponding information, if the adaptive driving style function switch status is on, the adaptive driving strategy can be adjusted according to the current driver's driving behavior score. By analyzing the driver's driving style, when the driver turns on the adaptive driving strategy, a personalized driving strategy can be provided to the driver based on the analysis results to improve the driver's driving experience.

[0117] In addition, during the driving style analysis, the cloud can perform corresponding analysis processes based on different databases, for example, Figure 3 , showing a schematic diagram of the data analysis process provided in an embodiment of the present invention, wherein GreenPlum is a database based on the MPP architecture and PostgreSQL open source database technology, referred to as GP; Doris Database (DorisDB) is a real-time analytical database based on the MPP (Massive Parallel Processing) architecture, designed to support efficient online analytical processing (OLAP) and complex queries, and is suitable for big data analysis scenarios; SeaTunnel is a high-performance, distributed data integration platform, mainly used for efficient synchronization, conversion and processing of large-scale data between different data sources, hereinafter referred to as SE; and DolphinScheduler can be used to provide a visual, distributed, and highly available workflow scheduling platform for the orchestration and automated management of big data tasks, hereinafter referred to as DS, etc. The corresponding process may include:

[0118] 1. All data reported by the cloud will be stored in OpenGemini, including the vehicle's VIN code, user ID, and each signal data reported every second.

[0119] 2. Use DS to schedule the data in OpenGemini every day and calculate the working condition information and write it into the GP detailed table.

[0120] 3. Data Analysis Process: ① For simple metrics, SQL is used to perform offline calculations directly on the detailed data tables in GP, ​​and the calculated metrics are inserted into the driving metric statistics table. ② For complex metrics, Flink programs are used to perform offline calculations and then update and insert them into the driving metric statistics table.

[0121] 4. Calculate the driving style table by associating the driving index statistics table with the driving index upper limit configuration table and the operating condition coefficient table. (The two configuration tables correspond to the score proportions and operating condition proportions of each driving index when calculating the driving style. The main calculation logic of the driving style table is to calculate the user's driving score for the past 100 hours based on the cumulative 100 hours of the driving index statistics table.)

[0122] 5. The driving style table is exported by PG through SE (data integration tool), then imported into Doris, and a virtual view is established for the back-end interface to perform data query.

[0123] Through the above process, by collecting the vehicle signals corresponding to the vehicle, the vehicle signals are converted into driving indicators that can be used to analyze the driver's driving style, and then analyzed and calculated in combination with the corresponding configuration table to achieve the driver's style evaluation. Based on the evaluation results, it is convenient to analyze the driver's driving style so as to provide the driver with more personalized driving content and enhance the driver's driving experience. The evaluation results can also provide corresponding references for the research and development and improvement of vehicle manufacturers to improve the vehicle's controllability and safety.

[0124] It should be noted that for the sake of simplicity, the method embodiments are described as a series of actions. However, those skilled in the art should be aware that the embodiments of the present invention are not limited by the order of the actions described, because according to the embodiments of the present invention, certain steps can be performed in other orders or simultaneously. Secondly, those skilled in the art should also be aware that the embodiments described in this specification are all preferred embodiments, and the actions involved are not necessarily required by the embodiments of the present invention.

[0125] Reference Figure 4 , shows a structural block diagram of a driving behavior analysis device provided by an embodiment of the present invention, which may specifically include the following modules:

[0126] A signal acquisition module 401 is configured to acquire a first vehicle signal corresponding to a vehicle in a first vehicle trip;

[0127] An index processing module 402 is configured to perform index processing on the first vehicle signal to obtain a corresponding first driving index;

[0128] The analysis module 403 is configured to obtain a configuration table for the first driving index, and perform a driving behavior analysis on the driver based on the configuration table and the first driving index to obtain driving style data corresponding to the driver.

[0129] In some feasible implementations, the indicator processing module 402 is specifically configured to:

[0130] Obtaining index conditions corresponding to various first vehicle signals;

[0131] The first vehicle signal is indexed according to the indexing condition to obtain a corresponding first driving index.

[0132] In some feasible implementations, the configuration table includes at least a driving index upper limit configuration table and a working condition coefficient configuration table, and the analysis module 403 is specifically configured to:

[0133] Obtaining an indicator upper limit value corresponding to the first driving indicator from the driving indicator upper limit configuration table;

[0134] Obtaining an indicator weight corresponding to the first driving indicator from the operating condition coefficient configuration table;

[0135] Obtaining the driving time corresponding to the vehicle;

[0136] performing a standardized conversion on the first driving index according to the driving duration to obtain a second driving index, wherein the first driving index is descriptive information of the driving behavior actually performed by the driver, and the second driving index is descriptive information of the driving behavior performed within a preset duration;

[0137] Evaluate according to the driving duration, the indicator upper limit, the indicator weight, and the second driving indicator to obtain a driving indicator score corresponding to the second driving indicator;

[0138] Driving style data of the driver is constructed based on the driving duration, the first driving index, the second driving index, and the driving index score.

[0139] In some feasible implementations, the analysis module 403 is specifically configured to:

[0140] If the driving duration is greater than or equal to a preset duration, calculating the first driving index and the driving duration to obtain a second driving index corresponding to the first driving index;

[0141] If the driving time is less than the preset time, the driving time and the preset time are used to calculate the actual ratio of the driving time to the preset time;

[0142] The actual duration ratio, the indicator upper limit value, and the first driving indicator are used to perform a calculation to obtain a second driving indicator corresponding to the first driving indicator.

[0143] In some feasible implementations, the analysis module 403 is specifically configured to:

[0144] calculating a quotient between the second driving index and the index upper limit value;

[0145] If the driving duration is greater than or equal to the preset duration, selecting the smaller value between the quotient and the preset threshold as the target value, and performing an evaluation using the target value and the indicator weight to obtain a driving indicator score corresponding to the second driving indicator;

[0146] If the driving duration is less than the preset duration, the quotient and the indicator weight are used to perform an evaluation to obtain a driving indicator score corresponding to the second driving indicator.

[0147] In some feasible implementations, the driving style data is a driving style table, and the analysis module 403 is specifically configured to:

[0148] Obtaining the user identity corresponding to the driver and the vehicle identification of the vehicle;

[0149] A driving style table of the driver is constructed using the user identity, the vehicle identity, the driving duration, the first driving index, the second driving index, and the driving index score.

[0150] Some possible implementations also include:

[0151] a data acquisition module, configured to acquire a second vehicle signal corresponding to the vehicle in a second vehicle trip, wherein a first trip time point corresponding to the first vehicle trip is before a trip time point of the second vehicle trip;

[0152] a processing module, configured to perform index processing on the second vehicle signal to obtain a corresponding third driving index;

[0153] The incremental processing module is configured to perform cumulative calculation on the same driving index by using the first driving index and the third driving index to obtain a corresponding fourth driving index.

[0154] Some possible implementations also include:

[0155] an invalidation processing module, configured to delete, based on a chronological order, driving indicators before a preset time period in the fourth driving indicator to obtain a corresponding target driving indicator;

[0156] The behavior analysis module 403 is used to analyze the driver's driving behavior according to the configuration table and the target driving index to obtain the driving style data corresponding to the driver.

[0157] In some feasible implementations, the first vehicle signal includes at least one of vehicle speed information, brake pedal status, maximum longitudinal deceleration within 1 second, maximum longitudinal acceleration within 1 second, maximum lateral deceleration within 1 second, maximum lateral acceleration within 1 second, actual accelerator pedal position, and collision time;

[0158] The indexing conditions include a first trigger condition for the vehicle speed information, a second trigger condition for the brake pedal state, a third trigger condition and a fourth trigger condition for the maximum longitudinal deceleration within 1 second, a fifth trigger condition for the actual position of the accelerator pedal, a sixth trigger condition for the collision time, and a seventh trigger condition for at least one of the maximum longitudinal deceleration within 1 second, the maximum longitudinal acceleration within 1 second, the maximum lateral deceleration within 1 second, and the maximum lateral acceleration within 1 second;

[0159] The first driving index includes at least one of the number of speeding, the number of braking, the number of sudden deceleration, the number of extremely sudden deceleration, collision information, and a ride comfort detection result.

[0160] In some feasible implementations, the indicator processing module 402 is specifically configured to:

[0161] Processing the vehicle speed information according to the first trigger condition to obtain the number of speeding times;

[0162] Processing the brake pedal state according to the second trigger condition to obtain the number of braking times;

[0163] Processing the maximum longitudinal deceleration within 1 second according to the third trigger condition and / or the actual position of the accelerator pedal according to the fifth trigger condition to obtain the number of rapid decelerations;

[0164] Processing the maximum longitudinal deceleration within 1 second according to the fourth trigger condition to obtain the number of urgent decelerations;

[0165] processing the collision time according to the sixth trigger condition to obtain the collision information;

[0166] The maximum longitudinal deceleration within 1 second, the maximum longitudinal acceleration within 1 second, the maximum lateral deceleration within 1 second, and the maximum lateral acceleration within 1 second are processed according to the seventh trigger condition to obtain the smoothness detection result.

[0167] As for the device embodiment, since it is basically similar to the method embodiment, the description is relatively simple, and the relevant parts can be referred to the partial description of the method embodiment.

[0168] An embodiment of the present invention further provides an electronic device, including:

[0169] one or more processors; and

[0170] One or more machine-readable media having instructions stored thereon, when executed by the one or more processors, enable the electronic device to perform the method described in the embodiment of the present invention.

[0171] An embodiment of the present invention further provides a computer-readable storage medium having instructions stored thereon, which, when executed by one or more processors, causes the processors to execute the method described in the embodiment of the present invention.

[0172] The various embodiments in this specification are described in a progressive manner, and each embodiment focuses on the differences from other embodiments. The same or similar parts between the various embodiments can be referenced to each other.

[0173] It should be understood by those skilled in the art that the embodiments of the present invention may be provided as methods, apparatuses, or computer program products. Therefore, the embodiments of the present invention may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the embodiments of the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, EEPROM, Flash, and eMMC, etc.) containing computer-usable program code.

[0174] The embodiments of the present invention are described with reference to the flowcharts and / or block diagrams of the methods, terminal devices (systems), and computer program products according to the embodiments of the present invention. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of the processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing terminal device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing terminal device generate instructions for implementing the process in the flowchart and / or block diagram. Figure 1 a process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0175] These computer program instructions may also be stored in a computer readable memory that can direct a computer or other programmable data processing terminal device to operate in a specific manner, so that the instructions stored in the computer readable memory produce a manufactured product including an instruction device, which implements the process Figure 1 a process or multiple processes and / or boxes Figure 1 The function specified in one or more boxes.

[0176] These computer program instructions can also be loaded onto a computer or other programmable data processing terminal device so that a series of operating steps are executed on the computer or other programmable terminal device to produce a computer-implemented process, thereby providing instructions for executing on the computer or other programmable terminal device to implement the process. Figure 1 a process or multiple processes and / or boxes Figure 1 A step that specifies a function in one or more boxes.

[0177] Although the preferred embodiments of the present invention have been described, those skilled in the art may make additional changes and modifications to these embodiments once they become aware of the basic creative concepts. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments and all changes and modifications that fall within the scope of the embodiments of the present invention.

[0178] Finally, it should be noted that, in this document, relational terms such as first and second, etc., are used only to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any actual relationship or order between these entities or operations. Moreover, the terms "comprises," "comprising," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or terminal device that includes a series of elements includes not only those elements, but also other elements not explicitly listed, or elements inherent to such process, method, article, or terminal device. In the absence of further limitations, an element defined by the phrase "comprising a ..." does not exclude the presence of additional identical elements in the process, method, article, or terminal device that includes the element.

[0179] The above describes in detail a driving behavior analysis method and a driving behavior analysis device provided by the present invention. Specific examples are used herein to illustrate the principles and implementation methods of the present invention. The description of the above embodiments is only intended to help understand the method and core concept of the present invention. At the same time, for those skilled in the art, according to the concept of the present invention, there may be changes in the specific implementation methods and application scopes. In summary, the contents of this specification should not be understood as limiting the present invention.

Claims

1. A method for analyzing driving behavior, characterized in that: include: Acquire a first vehicle signal corresponding to the vehicle in a first vehicle trip; performing indexing processing on the first vehicle signal to obtain a corresponding first driving index; A configuration table for the first driving index is obtained, and a driving behavior analysis of the driver is performed based on the configuration table and the first driving index to obtain driving style data corresponding to the driver.

2. The method according to claim 1, characterized in that The indexing process of the first vehicle signal to obtain a corresponding first driving index includes: Obtaining index conditions corresponding to various first vehicle signals; The first vehicle signal is indexed according to the indexing condition to obtain a corresponding first driving index.

3. The method according to claim 1, characterized in that The configuration table includes at least a driving index upper limit configuration table and a working condition coefficient configuration table. The driving behavior analysis of the driver is performed based on the configuration table and the first driving index to obtain the driving style data corresponding to the driver, including: Obtaining an indicator upper limit value corresponding to the first driving indicator from the driving indicator upper limit configuration table; Obtaining an indicator weight corresponding to the first driving indicator from the operating condition coefficient configuration table; Obtaining the driving time corresponding to the vehicle; performing a standardized conversion on the first driving index according to the driving duration to obtain a second driving index, wherein the first driving index is descriptive information of the driving behavior actually performed by the driver, and the second driving index is descriptive information of the driving behavior performed within a preset duration; Evaluate according to the driving duration, the indicator upper limit, the indicator weight, and the second driving indicator to obtain a driving indicator score corresponding to the second driving indicator; Driving style data of the driver is constructed based on the driving duration, the first driving index, the second driving index, and the driving index score.

4. The method according to claim 3, characterized in that The step of performing a standardized conversion on the first driving index according to the driving duration to obtain a second driving index includes: If the driving duration is greater than or equal to a preset duration, calculating the first driving index and the driving duration to obtain a second driving index corresponding to the first driving index; If the driving time is less than the preset time, the driving time and the preset time are used to calculate the actual ratio of the driving time to the preset time; The actual duration ratio, the indicator upper limit value, and the first driving indicator are used to perform a calculation to obtain a second driving indicator corresponding to the first driving indicator.

5. The method according to claim 3 or 4, characterized in that The evaluating according to the driving duration, the indicator upper limit, the indicator weight, and the second driving indicator to obtain a driving indicator score corresponding to the second driving indicator includes: calculating a quotient between the second driving index and the index upper limit value; If the driving duration is greater than or equal to the preset duration, selecting the smaller value between the quotient and the preset threshold as the target value, and performing an evaluation using the target value and the indicator weight to obtain a driving indicator score corresponding to the second driving indicator; If the driving duration is less than the preset duration, the quotient and the indicator weight are used to perform an evaluation to obtain a driving indicator score corresponding to the second driving indicator.

6. The method according to claim 3, characterized in that The driving style data is a driving style table, and constructing the driving style data of the driver based on the driving duration, the first driving index, the second driving index, and the driving index score includes: Obtaining the user identity corresponding to the driver and the vehicle identification of the vehicle; A driving style table of the driver is constructed using the user identity, the vehicle identity, the driving duration, the first driving index, the second driving index, and the driving index score.

7. The method according to claim 1, characterized in that Also includes: acquiring a second vehicle signal corresponding to the vehicle in a second vehicle trip, wherein a first trip time point corresponding to the first vehicle trip is before a trip time point of the second vehicle trip; performing index processing on the second vehicle signal to obtain a corresponding third driving index; For the same driving index, the first driving index and the third driving index are cumulatively calculated to obtain a corresponding fourth driving index.

8. The method according to claim 7, characterized in that Also includes: Based on the time sequence, deleting the driving indicators before the preset time period in the fourth driving indicator to obtain the corresponding target driving indicator; The driver's driving behavior is analyzed according to the configuration table and the target driving index to obtain driving style data corresponding to the driver.

9. The method according to claim 2, characterized in that The first vehicle signal includes at least one of vehicle speed information, brake pedal status, maximum longitudinal deceleration within 1 second, maximum longitudinal acceleration within 1 second, maximum lateral deceleration within 1 second, maximum lateral acceleration within 1 second, actual accelerator pedal position, and collision time; The indexing conditions include a first trigger condition for the vehicle speed information, a second trigger condition for the brake pedal state, a third trigger condition and a fourth trigger condition for the maximum longitudinal deceleration within 1 second, a fifth trigger condition for the actual position of the accelerator pedal, a sixth trigger condition for the collision time, and a seventh trigger condition for at least one of the maximum longitudinal deceleration within 1 second, the maximum longitudinal acceleration within 1 second, the maximum lateral deceleration within 1 second, and the maximum lateral acceleration within 1 second; The first driving index includes at least one of the number of speeding, the number of braking, the number of sudden deceleration, the number of extremely sudden deceleration, collision information, and a ride comfort detection result.

10. The method according to claim 9, characterized in that The indexing process of the first vehicle signal according to the indexing condition to obtain a corresponding first driving index includes at least one of the following: Processing the vehicle speed information according to the first trigger condition to obtain the number of speeding times; Processing the brake pedal state according to the second trigger condition to obtain the number of braking times; Processing the maximum longitudinal deceleration within 1 second according to the third trigger condition and / or the actual position of the accelerator pedal according to the fifth trigger condition to obtain the number of rapid decelerations; Processing the maximum longitudinal deceleration within 1 second according to the fourth trigger condition to obtain the number of urgent decelerations; processing the collision time according to the sixth trigger condition to obtain the collision information; The maximum longitudinal deceleration within 1 second, the maximum longitudinal acceleration within 1 second, the maximum lateral deceleration within 1 second, and the maximum lateral acceleration within 1 second are processed according to the seventh trigger condition to obtain the smoothness detection result.

11. A driving behavior analysis device, characterized in that: include: a signal acquisition module, configured to acquire a first vehicle signal corresponding to the vehicle during a first vehicle trip; an index processing module, configured to perform index processing on the first vehicle signal to obtain a corresponding first driving index; The analysis module is configured to obtain a configuration table for the first driving index, and perform a driving behavior analysis on the driver based on the configuration table and the first driving index to obtain driving style data corresponding to the driver.

12. An electronic device, characterized in that: include: one or more processors; and One or more machine-readable media having instructions stored thereon, when executed by the one or more processors, cause the electronic device to perform the method according to any one of claims 1 to 10.

13. A computer-readable storage medium having instructions stored thereon, which, when executed by one or more processors, cause the processors to perform the method according to any one of claims 1 to 10.

Images