Methods, devices, equipment, and media for assessing driving behavior

Abstract

This invention discloses a method, apparatus, device, and medium for evaluating driving behavior, relating to the field of intelligent transportation technology. The method includes: determining auxiliary trajectory points from among the candidate trajectory points based on the candidate direction angles corresponding to adjacent candidate trajectory points of the target vehicle; using a preset time period prior to the acquisition time of each auxiliary trajectory point as a candidate detection time period for each auxiliary trajectory point, and determining a target trajectory point from among the auxiliary trajectory points based on the average driving speed of the target vehicle within each candidate detection time period; and evaluating the driving behavior of the driver of the target vehicle within the target time period based on the number of target trajectory points. This invention helps to strengthen the supervision of drivers' safe driving behavior in turning scenarios, enabling timely correction of poor driving behavior and reducing the probability of accidents caused by insufficient driver observation in turning scenarios.

Description

Technical Field

[0001] This invention relates to the field of intelligent transportation technology, and in particular to a method, apparatus, device, and medium for evaluating driving behavior. Background Technology

[0002] In today's society, with the expansion of cities and the increase in population density, industrial and logistics demands continue to grow, leading to a greater need for commercial vehicles in delivery and transportation. Commercial vehicles account for 70% of road transport capacity. As the primary means of operational logistics, they not only bring significant economic benefits to the country but also serve as a source of income for transportation companies, fleets, and individual drivers. Due to the nature of their operation, commercial vehicles also bear greater responsibilities and risks.

[0003] In my country, the proportion of road traffic accidents involving commercial vehicles is far higher than the proportion of commercial vehicles in the total number of vehicles. Due to their greater weight and more difficult handling, commercial vehicles are more prone to causing serious accidents, posing a significant threat to driver safety and resulting in substantial losses for logistics and transportation companies. Improving road safety for commercial vehicles is therefore urgently needed. In addition to installing various monitoring devices, analyzing driving behavior to enhance safety is also an effective regulatory approach.

[0004] Current driving behavior analysis lacks analysis of whether vehicles slow down when turning, resulting in insufficient supervision of whether vehicles are driving safely in this scenario, creating safety hazards for the vehicles themselves and other road users. Summary of the Invention

[0005] This invention provides a method, apparatus, device, and medium for assessing driving behavior, in order to address the safety hazards posed to vehicles and other road users due to the current lack of technology in the industry to analyze whether vehicles slow down during turns.

[0006] According to one aspect of the present invention, a method for evaluating driving behavior is provided, comprising:

[0007] Obtain at least two candidate trajectory points generated by the target vehicle within the target time period, and determine the candidate orientation angle corresponding to the target vehicle when it is at each of the candidate trajectory points;

[0008] Based on the candidate direction angles corresponding to adjacent candidate trajectory points of the target vehicle, auxiliary trajectory points are determined from each candidate trajectory point; wherein, the auxiliary trajectory point is the candidate trajectory point corresponding to when the target vehicle makes a turning phenomenon;

[0009] A preset time period prior to the acquisition time of each of the auxiliary trajectory points is used as a candidate detection time period corresponding to each of the auxiliary trajectory points. The target trajectory point is determined from each of the auxiliary trajectory points based on the average driving speed of the target vehicle within each of the candidate detection time periods. The target trajectory point is the auxiliary trajectory point corresponding to the target detection time period, and the target detection time period is the candidate detection time period when the average driving speed of the target vehicle is less than a speed threshold.

[0010] Based on the number of target trajectory points, the driving behavior of the driver of the target vehicle during the target time period is evaluated.

[0011] According to another aspect of the present invention, a device for evaluating driving behavior is provided, comprising:

[0012] The candidate orientation angle determination module is used to acquire at least two candidate trajectory points generated by the target vehicle within a target time period, and determine the candidate orientation angle corresponding to the target vehicle when it is at each of the candidate trajectory points;

[0013] An auxiliary trajectory point determination module is used to determine an auxiliary trajectory point from each of the candidate trajectory points based on the candidate direction angles corresponding to the adjacent candidate trajectory points of the target vehicle; wherein, the auxiliary trajectory point is the candidate trajectory point corresponding to when the target vehicle turns;

[0014] The target trajectory point determination module is used to take a preset time period before the acquisition time of each of the auxiliary trajectory points as a candidate detection time period corresponding to each of the auxiliary trajectory points, and determine the target trajectory point from each of the auxiliary trajectory points according to the average driving speed of the target vehicle in each of the candidate detection time periods; wherein, the target trajectory point is an auxiliary trajectory point corresponding to the target detection time period, and the target detection time period is a candidate detection time period in which the average driving speed of the target vehicle is less than a speed threshold;

[0015] The driving behavior assessment module is used to assess the driving behavior of the driver of the target vehicle within the target time period based on the number of target trajectory points.

[0016] According to another aspect of the present invention, an electronic device is provided, the electronic device comprising:

[0017] At least one processor; and

[0018] A memory communicatively connected to the at least one processor; wherein,

[0019] The memory stores a computer program that can be executed by the at least one processor, the computer program being executed by the at least one processor to enable the at least one processor to perform the driving behavior evaluation method according to any one of the present invention.

[0020] According to another aspect of the present invention, a computer-readable storage medium is provided, the computer-readable storage medium storing computer instructions for causing a processor to execute and implement the driving behavior evaluation method according to any one of the present invention.

[0021] This invention identifies auxiliary trajectory points corresponding to when a target vehicle turns among candidate trajectory points of the target vehicle, and further identifies target trajectory points among the auxiliary trajectory points where the target vehicle exhibits deceleration and observation behavior. Based on the number of target trajectory points, the driving behavior of the target vehicle's driver within a target time period is evaluated. This achieves the effect of assessing whether the target vehicle's driver habitually decelerates and observes while turning, which helps strengthen the supervision of drivers' safe driving behavior in turning scenarios, enabling timely correction of poor driving behavior, reducing the probability of accidents caused by inadequate driver observation in turning scenarios, and improving the driving safety of the vehicle itself and other road users.

[0022] It should be understood that the description in this section is not intended to identify key or essential features of the embodiments of the present invention, nor is it intended to limit the scope of the invention. Other features of the invention will become readily apparent from the following description. Attached Figure Description

[0023] To more clearly illustrate the technical solutions in the embodiments of the present invention, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0024] Figure 1 A flowchart illustrating a method for evaluating driving behavior provided in Embodiment 1 of the present invention;

[0025] Figure 2A A flowchart illustrating a method for evaluating driving behavior provided in Embodiment 2 of the present invention;

[0026] Figure 2B This is a schematic diagram of a candidate orientation angle and orientation angle difference provided in Embodiment 2 of the present invention;

[0027] Figure 3 A flowchart illustrating a method for evaluating driving behavior provided in Embodiment 3 of the present invention;

[0028] Figure 4 This is a schematic diagram of the structure of a driving behavior assessment device provided in Embodiment 4 of the present invention;

[0029] Figure 5 This is a schematic diagram of the structure of an electronic device that implements the driving behavior evaluation method of the present invention. Detailed Implementation

[0030] To enable those skilled in the art to better understand the present invention, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings of the embodiments of the present invention. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort should fall within the scope of protection of the present invention.

[0031] It should be noted that the terms "candidate," "target," "auxiliary," "preceding," "first," "second," "abnormal," "actual," and "best," etc., used in the specification, claims, and accompanying drawings of this invention are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of the invention described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0032] Because drivers, especially in large vehicles, have blind spots when observing their side mirrors, failure to slow down and observe before turning can easily lead to accidents. In recent years, some areas in cities like Nanjing and Shanghai have begun piloting the new traffic rule of "stopping before turning," requiring large vehicles to stop and observe road conditions before making a right turn. Therefore, this invention uses low-speed driving (including stopping completely) before turning as an indicator of driving behavior, which helps to effectively identify this behavior in the early stages of this regulation.

[0033] Example 1

[0034] Figure 1This is a flowchart of a driving behavior assessment method provided in Embodiment 1 of the present invention. This embodiment is applicable to assessing whether the driver of a target vehicle habitually slows down to observe when turning. The method can be executed by a driving behavior assessment device, which can be implemented in hardware and / or software, such as through a monitoring platform. Figure 1 As shown, the method includes:

[0035] S101. Obtain at least two candidate trajectory points generated by the target vehicle within the target time period, and determine the candidate direction angle corresponding to the target vehicle when it is at each candidate trajectory point.

[0036] The target vehicle refers to the vehicle driven by the driver whose driving behavior needs to be evaluated. This evaluation allows for effective monitoring of the driver's actions. The target vehicle can be a commercial vehicle such as a ride-hailing vehicle, bus, or truck, or a private car. The type of vehicle can be expanded or adjusted according to specific business needs. For example, if the business need is for a commercial vehicle monitoring platform to evaluate and monitor the driving behavior of commercial vehicle drivers, then the target vehicle could be a ride-hailing vehicle, bus, or truck. Conversely, if the business need is for a transportation department monitoring platform to assess and monitor whether drivers with a history of poor driving behavior continue to exhibit such behavior, then the target vehicle could be a private car driven by that driver.

[0037] During the vehicle's journey, the monitoring platform periodically collects the vehicle's location data and generates trajectory points based on these locations. Candidate trajectory points refer to the trajectory points generated by the target vehicle within a target time period. This target time period is derived from historical timeframes and can be customized to meet specific business needs. For example, to ensure the richness of the driving data, the historical time period containing the most trajectory points can be used as the target time period; conversely, to ensure the timeliness of the driving data, the historical time period closest to the current time can be used as the target time period. The specific duration of the target time period can also be set and adjusted according to actual business requirements.

[0038] The direction angle refers to the angle formed by the direction line of the target vehicle's travel direction and the north-south direction. It can be understood that the candidate direction angle refers to the direction angle corresponding to the target vehicle when it is at each candidate trajectory point.

[0039] In one implementation, the monitoring platform matches the collection time of each trajectory point in the trajectory point set with the target time period. Based on the matching results, it selects trajectory points whose collection time belongs to the target time period as at least two candidate trajectory points generated by the target vehicle within the target time period. The trajectory point set is generated based on the collected trajectory points of the target vehicle across all historical times.

[0040] The candidate orientation angles corresponding to the target vehicle when it is at each candidate trajectory point can be determined in two ways, including but not limited to the following:

[0041] 1) When the monitoring platform collects the location of any target vehicle, it also uses the vehicle's attitude sensors, such as a three-axis gyroscope, a three-axis accelerometer, or a three-axis electronic compass, to collect the vehicle's orientation angle at that location. Then, when the monitoring platform creates trajectory points based on each vehicle's location, it uses the associated orientation angle as the data label for each trajectory point. For example, assuming the trajectory point created based on any vehicle's location is trajectory point A, and the orientation angle of the target vehicle at that location is angle 1, then "angle 1" will be used as the data label for trajectory point A.

[0042] After the monitoring platform obtains at least two candidate trajectory points generated by the target vehicle within the target time period, it determines the candidate direction angle corresponding to the target vehicle when it is at each candidate trajectory point based on the direction angle recorded in the data label of each candidate trajectory point.

[0043] 2) After the monitoring platform obtains at least two candidate trajectory points generated by the target vehicle within the target time period, it further determines the longitude and latitude of each candidate trajectory point. Then, based on the longitude difference and latitude difference between each candidate trajectory point, it calculates the candidate direction angle corresponding to the target vehicle when it is at each candidate trajectory point.

[0044] S102. Based on the candidate direction angles corresponding to the target vehicle at adjacent candidate trajectory points, determine the auxiliary trajectory points from each candidate trajectory point.

[0045] The auxiliary trajectory point is the candidate trajectory point corresponding to the target vehicle's turning behavior. That is, if the target vehicle turns at any candidate trajectory point, that candidate trajectory point is used as the auxiliary trajectory point. It can be understood that turning includes left turns and right turns, and the turning behavior is determined based on the candidate direction angles corresponding to adjacent candidate trajectory points.

[0046] When a vehicle is turning, a turning angle threshold is determined for each vehicle type based on the common minimum turning radius. For example, the minimum turning radius of heavy commercial vehicles is typically 6.5-10.5m, so the corresponding turning angle threshold for heavy commercial vehicles can be set to 30°. This turning angle threshold is used to determine whether the vehicle is turning. Further, a turning angle threshold suitable for the target vehicle is determined based on its vehicle type, and this threshold is used to identify whether the target vehicle is turning.

[0047] In one implementation, the monitoring platform calculates the direction angle difference between adjacent candidate trajectory points based on the candidate direction angles corresponding to the adjacent candidate trajectory points. Then, it compares each direction angle difference with the turning direction angle threshold adapted to the target vehicle. If any direction angle difference is greater than the turning direction angle threshold adapted to the target vehicle, it is determined that the target vehicle has turned. If any direction angle difference is less than or equal to the turning direction angle threshold adapted to the target vehicle, it is determined that the target vehicle has not turned.

[0048] For example, suppose that candidate trajectory point A collected at time T and candidate trajectory point B collected at time T+1 are two adjacent candidate trajectory points, and the difference in direction angle between candidate trajectory point A and candidate trajectory point B is θ1. Suppose that the turning direction angle threshold adapted to the target vehicle is θ. If θ1≤θ, it is determined that the target vehicle has not turned at this time; if θ1>θ, it is determined that the target vehicle has turned at candidate trajectory point B, and then candidate trajectory point B is used as an auxiliary trajectory point.

[0049] S103. The preset time period before the collection time of each auxiliary trajectory point is used as the candidate detection time period corresponding to each auxiliary trajectory point, and the target trajectory point is determined from each auxiliary trajectory point according to the average driving speed of the target vehicle in each candidate detection time period.

[0050] The preset time period can be set according to actual business needs. For example, the preset time period can be set to 5 seconds, that is, the target trajectory point is determined from each auxiliary trajectory point based on the average driving speed of the target vehicle in the first 5 seconds of each auxiliary trajectory point.

[0051] The target trajectory points are auxiliary trajectory points corresponding to the target detection time period, which is the candidate detection time period when the average driving speed of the target vehicle is less than a speed threshold. The speed threshold is used to determine whether the driver of the target vehicle is slowing down to observe. In other words, when the average driving speed is less than the speed threshold, it can be assumed that the driver of the target vehicle is slowing down to observe; when the average driving speed is greater than or equal to the speed threshold, it can be assumed that the driver of the target vehicle is not slowing down to observe. The speed threshold can be set according to actual business needs.

[0052] In one implementation, the monitoring platform determines candidate detection time periods for each auxiliary trajectory point based on a preset time period and the collection time of each auxiliary trajectory point. Then, based on at least one speed of the target vehicle collected within each candidate detection time period, the average speed of the target vehicle within each candidate detection time period is determined. For example, assuming the collection time of auxiliary trajectory point A is T, and the preset time period is 5 seconds, then T-5 is taken as the candidate detection time period corresponding to auxiliary trajectory point A, and the average speed of the target vehicle within T-5 is determined.

[0053] The monitoring platform compares the average speed of the target vehicle in each candidate detection time period with the speed threshold. If the average speed of the target vehicle in any candidate detection time period is less than the speed threshold, the auxiliary trajectory point corresponding to that candidate detection time period is taken as the target trajectory point. That is, when the driver of the target vehicle turns at the auxiliary trajectory point, there is a behavior of slowing down and observing. If the average speed of the target vehicle in any candidate detection time period is greater than or equal to the speed threshold, that is, when the driver of the target vehicle turns at the auxiliary trajectory point, there is no behavior of slowing down and observing.

[0054] Optionally, if the business requirement is to assess whether the target vehicle stopped to observe before turning, the monitoring platform determines the average driving speed of the target vehicle in each candidate detection time period, and then determines whether the average driving speed is zero. If it is, it is determined that the driver of the target vehicle stopped to observe when turning at the auxiliary trajectory point; otherwise, it is determined that the driver of the target vehicle did not stop to observe when turning at the auxiliary trajectory point.

[0055] S104. Based on the number of target trajectory points, evaluate the driving behavior of the driver of the target vehicle within the target time period.

[0056] Understandably, target trajectory points represent the trajectory points where the driver of the target vehicle stops to observe before turning, which is a positive driving behavior. Therefore, the more target trajectory points the target vehicle includes within the target time period, the better the driver's driving behavior within that time period; conversely, the fewer target trajectory points the target vehicle includes within the target time period, the worse the driver's driving behavior within that time period.

[0057] Based on this, the driving behavior of the driver of the target vehicle during the target time period is quantitatively scored according to the number of target trajectory points included by the target vehicle during the target time period, and then the driving behavior generated by the driver of the target vehicle during the target time period is evaluated based on the quantitative score.

[0058] Optionally, the number of target trajectory points included by the target vehicle within the target time period can be used as the quantitative score. For example, assuming the number of target trajectory points included by the target vehicle within the target time period is "30", then the quantitative score of the driver's driving behavior within the target time period is determined to be "30". It is understandable that the more target trajectory points, the higher the quantitative score.

[0059] Optionally, a quantitative score can be determined based on the ratio between the number of target trajectory points included by the target vehicle within the target time period and the number of auxiliary trajectory points included by the target vehicle within the target time period. It can be understood that the ratio between the number of target trajectory points and the number of auxiliary trajectory points represents the frequency with which the driver performs deceleration and observation behavior before all turning scenarios within the target time period; a higher ratio results in a higher quantitative score. For example, assuming the number of target trajectory points included by the target vehicle within the target time period is "30" and the number of auxiliary trajectory points included by the target vehicle within the target time period is "60", then the quantitative score for the driver's driving behavior within the target time period is determined to be (30 / 60) × 100 = 50.

[0060] After determining the quantitative score of the driver's driving behavior in the target vehicle within the target time period, the quality of the driver's driving behavior can be further evaluated based on the quantitative score and a scoring threshold. For example, assuming a scoring threshold of 60, if the quantitative score is greater than or equal to 60, the driver's driving behavior in the target vehicle within the target time period is judged as "excellent," thus encouraging the driver to maintain this level of performance. If the quantitative score is less than 60, the driver's driving behavior in the target vehicle within the target time period is judged as "poor," thus urging the driver to correct poor driving behavior in a timely manner, ensuring that they slow down and observe before turning, and optimizing their driving behavior.

[0061] This invention identifies auxiliary trajectory points corresponding to when a target vehicle turns among candidate trajectory points of the target vehicle, and further identifies target trajectory points among the auxiliary trajectory points where the target vehicle exhibits deceleration and observation behavior. Based on the number of target trajectory points, the driving behavior of the target vehicle's driver within a target time period is evaluated. This achieves the effect of assessing whether the target vehicle's driver habitually decelerates and observes while turning, which helps strengthen the supervision of drivers' safe driving behavior in turning scenarios, enabling timely correction of poor driving behavior, reducing the probability of accidents caused by inadequate driver observation in turning scenarios, and improving the driving safety of the vehicle itself and other road users.

[0062] Example 2

[0063] Figure 2A This is a flowchart of a driving behavior evaluation method provided in Embodiment 2 of the present invention. This embodiment further optimizes and expands the above embodiments and can be combined with the various optional implementation methods described above. Figure 2A As shown, the method includes:

[0064] S201. Obtain at least two candidate trajectory points generated by the target vehicle within the target time period. Based on the longitude and latitude of each candidate trajectory point, determine the longitude difference and latitude difference between adjacent candidate trajectory points.

[0065] S202. Based on the longitude difference and latitude difference, determine the candidate direction angle corresponding to the target vehicle when it is at each candidate trajectory point.

[0066] In one implementation, the ratio of the longitude difference to the latitude difference between adjacent candidate trajectory points is determined, and the candidate orientation angle corresponding to the target vehicle when it is at each candidate trajectory point is further determined based on the ratio.

[0067] By determining the longitude and latitude differences between adjacent candidate trajectory points based on their respective longitude and latitude, and then determining the candidate orientation angles corresponding to the target vehicle when it is located at each candidate trajectory point, the orientation angles can be identified using only the target vehicle's longitude and latitude values ​​without relying on sensor equipment. This achieves the effect of identifying the target vehicle's orientation angles at a low cost, and avoids the risk of sensor equipment failure due to sensor equipment malfunction, thus ensuring the stability and reliability of the target vehicle's orientation angle identification.

[0068] Optionally, the candidate orientation angles corresponding to the target vehicle at each candidate trajectory point can be determined using the following formula:

[0069]

[0070] Where θ represents the candidate orientation angle corresponding to the target vehicle when it is at any candidate trajectory point, Δlong represents the longitude difference between the candidate trajectory point and the preceding trajectory point, Δlat represents the latitude difference between the candidate trajectory point and the preceding trajectory point, and the preceding trajectory point is the candidate trajectory point that is adjacent to the candidate trajectory point and whose acquisition time is earlier than the candidate trajectory point.

[0071] For example, assuming candidate trajectory point A is adjacent to candidate trajectory point B and its acquisition time is earlier than that of candidate trajectory point B, then candidate trajectory point A is considered the preceding trajectory point of candidate trajectory point B. Assuming the longitude difference between candidate trajectory point A and candidate trajectory point B is Δlong1 and the latitude difference is Δlat1, then the candidate orientation angle θ1 corresponding to the target vehicle being at candidate trajectory point B is...

[0072] Through formula It can conveniently, quickly, and cost-effectively calculate the candidate orientation angles corresponding to the target vehicle when it is at each candidate trajectory point.

[0073] Optionally, after determining the candidate orientation angles corresponding to the target vehicle at each candidate trajectory point, the following may also be included:

[0074] The obtained candidate orientation angles are normalized so that they can be used correctly in subsequent calculations. This includes the following cases:

[0075] 1) When Δlong=Δlat=0, tanθ=NAN, which means that any candidate trajectory point has not been displaced relative to its preceding trajectory point. When the target vehicle is at the candidate trajectory point, the corresponding candidate direction angle θ is normalized to θ′=0.

[0076] 2) When Δlong=0 and Δlat>0, tanθ=0, which means that any candidate trajectory point moves due north relative to its predecessor trajectory point. In this case, there is no need to normalize the candidate direction angle θ corresponding to the target vehicle when it is at the candidate trajectory point.

[0077] 3) When Δlong=0 and Δlat<0, tanθ=-0, which means that any candidate trajectory point moves due south relative to its predecessor trajectory point. When the target vehicle is at the candidate trajectory point, the corresponding candidate direction angle θ is normalized to θ′=π.

[0078] 4) When Δlong<0 and Δlat=0, tanθ=-inf, which means that any candidate trajectory point moves due west relative to its predecessor trajectory point. When the target vehicle is at this candidate trajectory point, the corresponding candidate direction angle θ=arctan(-inf)=-0.5π, and after normalization, θ′=1.5π.

[0079] 5) When Δlong>0 and Δlat=0, tanθ=inf, which means that any candidate trajectory point moves due east relative to its predecessor trajectory point. At this time, there is no need to normalize the candidate direction angle θ corresponding to the target vehicle when it is at the candidate trajectory point.

[0080] 6) When Δlong>0 and Δlat>0, tanθ>0, it means that any candidate trajectory point moves relative to its predecessor trajectory point toward the first quadrant with the origin as the starting point. At this time, there is no need to normalize the candidate direction angle θ corresponding to the target vehicle when it is at the candidate trajectory point.

[0081] 7) When Δlong>0 and Δlat<0, tanθ<0, which means that any candidate trajectory point moves towards the second quadrant relative to its predecessor trajectory point. When the target vehicle is at the candidate trajectory point, the corresponding candidate direction angle θ is normalized to θ′=|θ|.

[0082] 8) When Δlong < 0 and Δlat < 0, tanθ > 0, which means that any candidate trajectory point moves towards the third quadrant relative to its preceding trajectory point. The normalized candidate direction angle θ corresponding to the target vehicle when it is at this candidate trajectory point is θ. ′ =θ+π.

[0083] 9) When Δlong < 0 and Δlat > 0, tanθ < 0, which means that any candidate trajectory point moves towards the fourth quadrant relative to its preceding trajectory point. The normalized candidate direction angle θ corresponding to the target vehicle when it is at this candidate trajectory point is θ. ′ = -θ + π.

[0084] S203. Based on the candidate direction angle of any candidate trajectory point and the candidate direction angle of the preceding trajectory point, determine the direction angle difference between the candidate trajectory point and the preceding trajectory point.

[0085] Among them, the preceding trajectory point is the candidate trajectory point that is adjacent to the candidate trajectory point and whose acquisition time is earlier than that of the candidate trajectory point.

[0086] For example, assuming candidate trajectory point A is adjacent to candidate trajectory point B and its acquisition time is earlier than that of candidate trajectory point B, then candidate trajectory point A is considered the preceding trajectory point of candidate trajectory point B. Assuming the candidate direction angle corresponding to the target vehicle being at candidate trajectory point A is θa, and the candidate direction angle corresponding to the target vehicle being at candidate trajectory point B is θb, then the difference in direction angle between candidate trajectory point B and the preceding trajectory point (candidate trajectory point A) is θb - θa.

[0087] Figure 2B This is a schematic diagram of a candidate orientation angle and orientation angle difference provided in Embodiment 2 of the present invention, as shown below. Figure 2B As shown, x T-1 x T and x T+1 Let θ represent the three candidate trajectory points respectively. xT This indicates that the target vehicle is located at candidate trajectory point x. T The corresponding candidate orientation angle, θ xT+1 This indicates that the target vehicle is located at candidate trajectory point x.T+1 The corresponding candidate direction angle, candidate trajectory point x T Candidate trajectory point x T+1 The preceding trajectory point, the candidate trajectory point x T+1 With candidate trajectory point x T The difference in direction angle between them is θ xTxT+1 N and E represent due north and due east, respectively.

[0088] S204. If the absolute value of the direction angle difference is greater than the first difference threshold, then the candidate trajectory point is used as an auxiliary trajectory point.

[0089] The first difference threshold represents the turning angle threshold that is compatible with the target vehicle model, and is used to determine whether the vehicle is turning.

[0090] For example, assuming the first difference threshold is 30°, and the direction angle difference between any candidate trajectory point and the previous trajectory point is θ, then when |θ|>30°, the candidate trajectory point is used as an auxiliary trajectory point, that is, the target vehicle turns at the candidate trajectory point.

[0091] Continue with Figure 2B Taking the candidate trajectory point x as an example for explanation, T+1 With candidate trajectory point x T The difference in direction angle between them is θ xTxT+1 Assuming the first difference threshold is 30°, if |θ xTxT+1 If |>30°, then the candidate trajectory point x T+1 As an auxiliary trajectory point, i.e., the target vehicle at the candidate trajectory point x T+1 A turning point occurred at that point.

[0092] By determining the direction angle difference between a candidate trajectory point and a preceding trajectory point based on the candidate direction angle of any candidate trajectory point and the candidate direction angle of the preceding trajectory point, if the absolute value of the direction angle difference is greater than the first difference threshold, the candidate trajectory point is used as an auxiliary trajectory point. Thus, the auxiliary trajectory point for the target vehicle to turn can be determined solely based on the direction angle difference, without relying on sensor equipment, and the turning behavior of the target vehicle can be identified at low cost.

[0093] S205. The preset time period before the collection time of each auxiliary trajectory point is used as the candidate detection time period corresponding to each auxiliary trajectory point, and the target trajectory point is determined from each auxiliary trajectory point according to the average driving speed of the target vehicle in each candidate detection time period.

[0094] Among them, the target trajectory point is the auxiliary trajectory point corresponding to the target detection time period, and the target detection time period is the candidate detection time period when the average driving speed of the target vehicle is less than the speed threshold.

[0095] S206. Based on the number of target trajectory points and the number of auxiliary trajectory points, determine the first quantity ratio of the target trajectory points relative to the auxiliary trajectory points.

[0096] S207. Based on the first quantity proportion, evaluate the driving behavior of the driver of the target vehicle within the target time period.

[0097] In one implementation, the driving behavior of the driver of the target vehicle during a target time period is evaluated using the following formula:

[0098]

[0099] Where y represents the quantitative score of the driving behavior of the driver of the target vehicle within the target time period. denoted by , x represents the number of target trajectory points, and N represents the number of auxiliary trajectory points.

[0100] By determining the first proportion of the target trajectory point relative to the auxiliary trajectory points based on the number of target trajectory points and the number of auxiliary trajectory points, the driving behavior of the driver of the target vehicle within the target time period is evaluated based on the first proportion. This evaluation is based on the frequency of the driver's deceleration and observation in turning scenarios, avoiding the problem of insufficient rationality and reliability in evaluating driving behavior solely based on the number of times the driver decelerates and observes in turning scenarios, thus ensuring the rationality and reliability of the driving behavior evaluation.

[0101] Optionally, after determining the direction angle difference between the candidate trajectory point and the preceding trajectory point, the method further includes:

[0102] A. If the absolute value of the direction angle difference is greater than the second difference threshold, then the candidate trajectory point is regarded as an abnormal trajectory point.

[0103] The second difference threshold is used to determine whether a vehicle is making a sharp turn. This is because a sharp turn produces a larger turning angle than a normal turn; therefore, the second difference threshold is set higher than the first difference threshold. Abnormal trajectory points are candidate trajectory points corresponding to when the target vehicle makes a sharp turn. The size of the second difference threshold can also be determined based on the minimum turning radius of the target vehicle, or in other words, based on the vehicle type. For example, the minimum turning radius of a heavy commercial vehicle is typically 6.5-10.5m, so the second difference threshold for heavy commercial vehicles can be set to 73°.

[0104] For example, assuming the second difference threshold is 73°, and the difference in direction angle between any candidate trajectory point and the previous trajectory point is θ, then when |θ|>73°, the candidate trajectory point is regarded as an abnormal trajectory point, that is, the target vehicle has made a sharp turn at the candidate trajectory point.

[0105] Continue with Figure 2B Taking the candidate trajectory point x as an example for explanation, T+1 With candidate trajectory point x T The difference in direction angle between them is θ xTxT+1 Assuming the first difference threshold is 73°, if |θ xTxT+1 If |>73°, then the candidate trajectory point x T+1 As an abnormal trajectory point, that is, the target vehicle at candidate trajectory point x T+1 A sharp turn occurred at that point.

[0106] B. Based on the number of abnormal trajectory points and the number of auxiliary trajectory points, determine the second proportion of abnormal trajectory points relative to auxiliary trajectory points.

[0107] C. Based on the second proportion, assess the driving behavior of the driver of the target vehicle during the target time period.

[0108] It is understandable that abnormal trajectory points represent the trajectory points where the driver of the target vehicle exhibits sharp turning behavior when turning, which is a negative driving behavior. Therefore, the fewer abnormal trajectory points the target vehicle includes in the target time period, the better the driver's driving behavior in the target time period; conversely, the more abnormal trajectory points the target vehicle includes in the target time period, the worse the driver's driving behavior in the target time period.

[0109] Based on this, the driving behavior of the driver of the target vehicle during the target time period is quantitatively scored according to the number of abnormal trajectory points included in the target vehicle during the target time period, and then the driving behavior generated by the driver of the target vehicle during the target time period is evaluated based on the quantitative score.

[0110] In one implementation, the driving behavior of the driver of the target vehicle during a target time period is evaluated using the following formula:

[0111]

[0112] Where y represents the quantitative score of the driving behavior of the driver of the target vehicle within the target time period. denoted by , x represents the number of abnormal trajectory points, and N represents the number of auxiliary trajectory points.

[0113] If the absolute value of the direction angle difference is greater than a second difference threshold, the candidate trajectory point is considered an abnormal trajectory point. The second difference threshold is greater than the first difference threshold, and the abnormal trajectory point is the candidate trajectory point corresponding to when the target vehicle makes a sharp turn. Based on the number of abnormal trajectory points and the number of auxiliary trajectory points, a second proportion of abnormal trajectory points relative to auxiliary trajectory points is determined. Based on this second proportion, the driving behavior of the target vehicle's driver within the target time period is evaluated.

[0114] Firstly, it achieves the effect of assessing whether the driver of the target vehicle has made a sharp turn, which helps to strengthen the supervision of drivers' safe driving behavior in turning scenarios, so as to correct the driver's bad driving behavior in a timely manner, reduce the probability of accidents caused by drivers' sharp turns in turning scenarios, and improve the driving safety of the vehicle itself and other traffic participants.

[0115] Secondly, it expands the dimensions of driving behavior assessment, enabling the assessment of driver behavior in turning scenarios from two dimensions: "whether to slow down and observe" and "whether there is a sharp turn," thereby further strengthening the supervision of drivers' safe driving behavior in turning scenarios.

[0116] Poor driving habits not only directly affect driving safety but also lead to poor fuel economy. Fuel consumption levels directly reflect driving economy.

[0117] Example 3

[0118] Figure 3 This is a flowchart of a driving behavior assessment method provided in Embodiment 3 of the present invention. This embodiment is applicable to assessing the level of fuel consumption generated by a driver driving a target vehicle. It further optimizes and expands the above embodiment and can be combined with the various optional implementation methods described above. For example... Figure 3 As shown, the method includes:

[0119] S301. Determine at least one instantaneous driving speed of the target vehicle during the target time period, and the target sub-time period corresponding to each instantaneous driving speed.

[0120] The target sub-time period refers to the sub-time period corresponding to each instantaneous driving speed within the target time period.

[0121] In one implementation, the monitoring platform collects driving data of the target vehicle, determines at least one instantaneous driving speed that occurred within the target time period based on the driving data, and determines the time corresponding to each instantaneous driving speed, and then determines the target sub-time period corresponding to each instantaneous driving speed based on the time set.

[0122] For example, assuming the target time period is T0-T100, and the times when the instantaneous driving speed "40km / h" occurs are T5-T10, T15-T30, and T67-T90, then T5-T10, T15-T30, and T67-T90 are collectively regarded as the target sub-time periods corresponding to the instantaneous driving speed "40km / h".

[0123] S302. Obtain the total amount of fuel consumed by the target vehicle at each instantaneous driving speed according to the target sub-time period, and use it as the total amount of fuel consumption corresponding to each instantaneous driving speed.

[0124] The target vehicle records its instantaneous fuel consumption in real time during its journey. The monitoring platform obtains the corresponding instantaneous fuel consumption from the target vehicle based on the target sub-time period corresponding to each instantaneous driving speed, and sums them up to calculate the total fuel consumption corresponding to each instantaneous driving speed.

[0125] For example, assuming the target sub-time period corresponding to the instantaneous driving speed v is T1-T5, the monitoring platform obtains the instantaneous fuel consumption O1 at time T1, the instantaneous fuel consumption O2 at time T2, the instantaneous fuel consumption O3 at time T3, the instantaneous fuel consumption O4 at time T4, and the instantaneous fuel consumption O5 at time T5 from the target vehicle. Then the total fuel consumption corresponding to the instantaneous driving speed v is O1+O2+O3+O4+O5.

[0126] S303. Determine the unit speed fuel consumption corresponding to each instantaneous driving speed based on the ratio between each instantaneous driving speed and the total fuel consumption corresponding to each instantaneous driving speed, and use this as the actual fuel consumption corresponding to each instantaneous driving speed.

[0127] Among them, fuel consumption per unit speed (actual fuel consumption) means the fuel consumption per unit vehicle speed, which can directly reflect the driver's economic efficiency in driving the target vehicle.

[0128] In one implementation, the actual fuel consumption corresponding to each instantaneous driving speed is determined using the following formula:

[0129]

[0130] Where, α i This represents the actual fuel consumption corresponding to the instantaneous driving speed i.i len(v) represents the total fuel consumption corresponding to the instantaneous driving speed i. i ) represents the number of times the instantaneous speed i occurs within the target time period.

[0131] S304. Based on the actual fuel consumption, evaluate the driving behavior of the driver of the target vehicle during the target time period.

[0132] Understandably, the lower the actual fuel consumption of the target vehicle during the target time period, the better the driver's driving behavior during that period; conversely, the higher the actual fuel consumption of the target vehicle during the target time period, the worse the driver's driving behavior during that period.

[0133] Based on this, the driving behavior of the driver of the target vehicle during the target time period is quantitatively scored according to the actual fuel consumption of the target vehicle during the target time period, and then the driving behavior generated by the driver of the target vehicle during the target time period is evaluated based on the quantitative score.

[0134] Optionally, a quantitative score can be determined based on the average fuel consumption corresponding to the actual fuel consumption at each instantaneous driving speed. After determining the quantitative score of the driver's driving behavior in the target vehicle within the target time period, the quality of the driver's driving behavior during the target time period can be further evaluated based on the quantitative score and a scoring threshold. For example, assuming a scoring threshold of 60, if the quantitative score is greater than or equal to 60, the driver's driving behavior in the target time period is judged as "excellent," thus encouraging the driver to maintain this level of performance; if the quantitative score is less than 60, the driver's driving behavior in the target time period is judged as "poor," thus urging the driver to correct poor driving behavior in a timely manner and optimize driving economy.

[0135] By determining at least one instantaneous driving speed of the target vehicle within a target time period, and the target sub-time periods corresponding to each instantaneous driving speed; obtaining the total fuel consumed by the target vehicle at each instantaneous driving speed based on the target sub-time periods, as the total fuel consumption corresponding to each instantaneous driving speed; determining the fuel consumption per unit speed corresponding to each instantaneous driving speed based on the ratio between each instantaneous driving speed and the total fuel consumption corresponding to each instantaneous driving speed, as the actual fuel consumption corresponding to each instantaneous driving speed; and evaluating the driving behavior of the target vehicle's driver within the target time period based on each actual fuel consumption.

[0136] Firstly, it achieves the effect of evaluating the driving economy of the target vehicle's driver, which is conducive to strengthening the supervision of the driver's driving economy, so as to correct the driver's bad driving behavior in a timely manner, improve the driver's driving economy, save fuel and protect the environment, and bring more economic benefits to commercial vehicles.

[0137] Secondly, it expands the dimensions of driving behavior assessment, enabling the assessment of driver behavior in turning scenarios from three dimensions: "whether to slow down and observe," "whether there is a sharp turn," and "driving economy," thereby further strengthening the supervision of driver behavior.

[0138] Optionally, the driving behavior of the driver of the target vehicle during the target time period may be evaluated based on the actual fuel consumption, including:

[0139] 1) In historical data, obtain the lowest fuel consumption per unit speed for the target vehicle model at each instantaneous driving speed, and use it as the optimal fuel consumption for each instantaneous driving speed.

[0140] Unlike other driving behavior indicators, which have road traffic safety regulations as a reference, vehicle fuel consumption levels lack objective evaluation standards. Different drivers exhibit different driving patterns, leading to varying fuel consumption levels. Therefore, it is necessary to introduce benchmark parameters to measure fuel consumption levels. The benchmark parameters for measuring fuel consumption levels differ for different vehicle models and instantaneous speeds; therefore, corresponding benchmark parameters need to be set for different vehicle models and instantaneous speeds.

[0141] In this embodiment, the benchmark parameter for measuring fuel consumption levels is recorded in a dynamically iterative two-dimensional data table constructed based on historical data, with dimensions of vehicle type and instantaneous driving speed. For any vehicle type and any instantaneous driving speed, the benchmark parameter is the lowest fuel consumption per unit speed that has occurred for that vehicle type and instantaneous driving speed. When a new fuel consumption per unit speed is generated, the two-dimensional data table iterates. If the table does not contain the dimension to which the latest fuel consumption per unit speed belongs, the size of the table is increased and the latest fuel consumption per unit speed is entered in the corresponding position; if the latest fuel consumption per unit speed is smaller than the benchmark parameter at the corresponding position in the table, the value at the corresponding position in the table is replaced with the latest fuel consumption per unit speed.

[0142] In one implementation, the monitoring platform matches and searches the target vehicle model and instantaneous driving speed in a two-dimensional data table to determine the lowest fuel consumption per unit speed (benchmark parameter) that the target vehicle model has ever experienced at each instantaneous driving speed, which is then used as the optimal fuel consumption for each instantaneous driving speed.

[0143] 2) Determine the unit fuel consumption assessment value of the target vehicle at each instantaneous driving speed based on the ratio between the actual fuel consumption and the optimal fuel consumption at each instantaneous driving speed.

[0144] The ratio between the actual fuel consumption and the optimal fuel consumption at each instantaneous driving speed reflects the degree of deviation between the actual fuel consumption and the optimal fuel consumption at each instantaneous driving speed. The greater the deviation, the worse the driver's driving economy, and the smaller the deviation, the better the driver's driving economy.

[0145] Optionally, the fuel consumption unit evaluation value corresponding to the target vehicle at each instantaneous driving speed can be determined using the following formula:

[0146]

[0147] in, α represents the unit evaluation value of fuel consumption corresponding to the instantaneous driving speed i. i , best α represents the optimal fuel consumption corresponding to the instantaneous driving speed i. i This represents the actual fuel consumption corresponding to the instantaneous driving speed i.

[0148] 3) Based on the product of the frequency of each instantaneous driving speed in the target time period and the evaluation value of each fuel consumption unit, determine the total evaluation value of fuel consumption of the target vehicle at each instantaneous driving speed in the target time period.

[0149] Optionally, the total estimated fuel consumption for the target vehicle at each instantaneous speed within the target time period can be determined using the following formula:

[0150]

[0151]

[0152] in, Freq represents the total estimated fuel consumption of the target vehicle at its instantaneous speed i within the target time period. i This represents the frequency of instantaneous speed i within the target time period. len(v) represents the fuel consumption per unit value corresponding to the instantaneous driving speed i. i ) represents the number of times the instantaneous speed i occurs within the target time period, len(v j This represents the total number of times each instantaneous driving speed occurs within the target time period.

[0153] 4) Based on the summation of the total fuel consumption assessment values ​​corresponding to each instantaneous driving speed, evaluate the driving behavior of the driver of the target vehicle during the target time period.

[0154] In one implementation, the driving behavior of the driver of the target vehicle during the target time period is quantitatively scored based on the sum of the total fuel consumption assessment values ​​corresponding to each instantaneous driving speed, and then the driving behavior generated by the driver of the target vehicle during the target time period is evaluated based on the quantitative score.

[0155] Optionally, the quantitative score can be determined using the following formula:

[0156]

[0157] Where y is the quantitative score. Represents the minimum instantaneous velocity v within the target time period. min To the maximum instantaneous velocity v max The summation of the total estimated fuel consumption values ​​corresponding to all instantaneous driving speeds.

[0158] By obtaining the lowest fuel consumption per unit speed for the target vehicle model at each instantaneous speed from historical data, this is taken as the optimal fuel consumption for each instantaneous speed. The ratio between the actual fuel consumption and the optimal fuel consumption at each instantaneous speed is used to determine the unit fuel consumption assessment value for the target vehicle at each instantaneous speed. The product of the frequency of each instantaneous speed within the target time period and the unit fuel consumption assessment value is used to determine the total fuel consumption assessment value for the target vehicle at each instantaneous speed within the target time period. The summation of the total fuel consumption assessment values ​​for each instantaneous speed is used to evaluate the driver's driving behavior within the target time period. By introducing the optimal fuel consumption as a benchmark parameter, the level of actual fuel consumption can be quantified, further improving the accuracy and reliability of the evaluation results for the driver's driving behavior within the target time period.

[0159] Optionally, this embodiment also provides a method for assessing driving behavior, including:

[0160] The first quantitative score is determined based on the first quantity percentage, the second quantitative score is determined based on the second quantity percentage, and the third quantitative score is determined based on the sum of the total fuel consumption assessment values ​​corresponding to each instantaneous driving speed. The first weight corresponding to the first quantitative score, the second weight corresponding to the second quantitative score, and the third weight corresponding to the third quantitative score are obtained. The first quantitative score, the second quantitative score, the third quantitative score, the first weight, the second weight, and the third weight are weighted and summed to determine the total quantitative score. The driving behavior of the driver of the target vehicle during the target time period is evaluated based on the total quantitative score.

[0161] The first weight, second weight, and third weight can be determined in the following way:

[0162] The Analytic Hierarchy Process (AHP) was used to quantify driving behavior and model it. The steps for constructing the model using AHP are: 1. Establishing a hierarchical model; 2. Constructing the judgment matrix; 3. Consistency check. When establishing the model hierarchy, it is divided into a target layer and a criterion layer from top to bottom. Safety and economy are set as the target layer, and the first, second, and third quantitative scores are set as the criterion layer. AHP determines the weights between factors at each level by constructing the judgment matrix, using relative scales to compare each factor pairwise, and using the ratios to construct the judgment matrix. Expert scoring is used when constructing the judgment matrix, i.e., senior engineers in the automotive and transportation field evaluate the importance ratios of each pairwise comparison of factors. Judgment matrices A_Safety and A_Economy are established for the overall target. After the judgment matrix passes the consistency check, the normalized eigenvector values ​​of the judgment matrix are the contributions of each criterion to the target, i.e., the first weight corresponding to the first quantitative score, the second weight corresponding to the second quantitative score, and the third weight corresponding to the third quantitative score under that target.

[0163] Example 4

[0164] Figure 4 This is a schematic diagram of the structure of a driving behavior assessment device provided in Embodiment 4 of the present invention. Figure 4 As shown, the device includes:

[0165] The candidate orientation angle determination module 41 is used to acquire at least two candidate trajectory points generated by the target vehicle within the target time period, and determine the candidate orientation angle corresponding to the target vehicle when it is at each candidate trajectory point;

[0166] The auxiliary trajectory point determination module 42 is used to determine auxiliary trajectory points from each candidate trajectory point based on the candidate direction angles corresponding to adjacent candidate trajectory points of the target vehicle; wherein, the auxiliary trajectory point is the candidate trajectory point corresponding to when the target vehicle turns.

[0167] The target trajectory point determination module 43 is used to take the preset time period before the collection time of each auxiliary trajectory point as the candidate detection time period corresponding to each auxiliary trajectory point, and determine the target trajectory point from each auxiliary trajectory point according to the average driving speed of the target vehicle in each candidate detection time period; wherein, the target trajectory point is the auxiliary trajectory point corresponding to the target detection time period, and the target detection time period is the candidate detection time period when the average driving speed of the target vehicle is less than the speed threshold.

[0168] The driving behavior assessment module 44 is used to assess the driving behavior of the driver of the target vehicle within the target time period based on the number of target trajectory points.

[0169] Optionally, the candidate orientation angle determination module 41 is specifically used for:

[0170] Based on the longitude and latitude of each candidate trajectory point, determine the longitude difference and latitude difference between adjacent candidate trajectory points;

[0171] Based on the longitude and latitude differences, the candidate orientation angles corresponding to the target vehicle when it is at each candidate trajectory point are determined.

[0172] Optionally, the candidate orientation angle determination module 41 is further used for:

[0173] The candidate orientation angles corresponding to the target vehicle at each candidate trajectory point are determined using the following formula:

[0174]

[0175] Where θ represents the candidate orientation angle corresponding to the target vehicle when it is at any candidate trajectory point, Δlong represents the longitude difference between the candidate trajectory point and the preceding trajectory point, Δlat represents the latitude difference between the candidate trajectory point and the preceding trajectory point, and the preceding trajectory point is the candidate trajectory point that is adjacent to the candidate trajectory point and whose acquisition time is earlier than the candidate trajectory point.

[0176] Optional, the auxiliary trajectory point determination module 42 is specifically used for:

[0177] Based on the candidate orientation angle of any candidate trajectory point and the candidate orientation angle of the preceding trajectory point, the orientation angle difference between the candidate trajectory point and the preceding trajectory point is determined; wherein, the preceding trajectory point is the candidate trajectory point that is adjacent to the candidate trajectory point and whose acquisition time is earlier than that of the candidate trajectory point;

[0178] If the absolute value of the direction angle difference is greater than the first difference threshold, then the candidate trajectory point is used as an auxiliary trajectory point.

[0179] Optional, driving behavior assessment module 44, specifically used for:

[0180] Based on the number of target trajectory points and the number of auxiliary trajectory points, determine the first quantity ratio of the target trajectory points relative to the auxiliary trajectory points;

[0181] Based on the first proportion, the driving behavior of the driver of the target vehicle during the target time period is evaluated.

[0182] Optionally, the device also includes a second driving behavior assessment module, specifically used for:

[0183] If the absolute value of the direction angle difference is greater than the second difference threshold, then the candidate trajectory point is regarded as an abnormal trajectory point; wherein, the second difference threshold is greater than the first difference threshold, and the abnormal trajectory point is the candidate trajectory point corresponding to the target vehicle making a sharp turn.

[0184] Based on the number of abnormal trajectory points and the number of auxiliary trajectory points, determine the second proportion of abnormal trajectory points relative to auxiliary trajectory points;

[0185] Based on the second percentage, the driving behavior of the driver of the target vehicle during the target time period is evaluated.

[0186] Optionally, the device also includes a third driving behavior assessment module, specifically used for:

[0187] Determine at least one instantaneous driving speed of the target vehicle during the target time period, and the target sub-time period corresponding to each instantaneous driving speed;

[0188] The total amount of fuel consumed by the target vehicle at each instantaneous driving speed is obtained based on the target sub-time period, and is used as the total fuel consumption corresponding to each instantaneous driving speed.

[0189] The fuel consumption per unit speed corresponding to each instantaneous driving speed is determined by the ratio between each instantaneous driving speed and the total fuel consumption corresponding to each instantaneous driving speed, and is taken as the actual fuel consumption corresponding to each instantaneous driving speed.

[0190] Based on the actual fuel consumption, the driving behavior of the driver of the target vehicle during the target time period is evaluated.

[0191] Optionally, the third driving behavior assessment module is also used for:

[0192] In historical data, the lowest fuel consumption per unit speed of the target vehicle model at each instantaneous driving speed is obtained as the optimal fuel consumption for each instantaneous driving speed.

[0193] The unit fuel consumption evaluation value of the target vehicle at each instantaneous driving speed is determined based on the ratio between the actual fuel consumption and the optimal fuel consumption at each instantaneous driving speed.

[0194] Based on the product of the frequency of each instantaneous driving speed in the target time period and the evaluation value of each fuel consumption unit, the total evaluation value of fuel consumption of the target vehicle at each instantaneous driving speed in the target time period is determined.

[0195] The driving behavior of the driver of the target vehicle during the target time period is evaluated by summing the total fuel consumption assessment values ​​corresponding to each instantaneous driving speed.

[0196] The driving behavior assessment device provided in the embodiments of the present invention can execute the driving behavior assessment method provided in any embodiment of the present invention, and has the corresponding functional modules and beneficial effects of the method execution.

[0197] Example 5

[0198] Figure 5 A schematic diagram of an electronic device 50 that can be used to implement embodiments of the present invention is shown. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as personal digital processors, cellular phones, smartphones, wearable devices (e.g., helmets, glasses, watches, etc.), and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely illustrative and are not intended to limit the implementation of the invention described and / or claimed herein.

[0199] like Figure 5 As shown, the electronic device 50 includes at least one processor 51 and a memory, such as a read-only memory (ROM) 52 and a random access memory (RAM) 53, communicatively connected to the at least one processor 51. The memory stores computer programs executable by the at least one processor. The processor 51 can perform various appropriate actions and processes based on the computer program stored in the ROM 52 or loaded into the RAM 53 from storage unit 58. The RAM 53 can also store various programs and data required for the operation of the electronic device 50. The processor 51, ROM 52, and RAM 53 are interconnected via a bus 54. An input / output (I / O) interface 55 is also connected to the bus 54.

[0200] Multiple components in electronic device 50 are connected to I / O interface 55, including: input unit 56, such as keyboard, mouse, etc.; output unit 57, such as various types of monitors, speakers, etc.; storage unit 58, such as disk, optical disk, etc.; and communication unit 59, such as network card, modem, wireless transceiver, etc. Communication unit 59 allows electronic device 50 to exchange information / data with other devices through computer networks such as the Internet and / or various telecommunications networks.

[0201] Processor 51 can be a variety of general-purpose and / or special-purpose processing components with processing and computing capabilities. Some examples of processor 51 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various special-purpose artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, a digital signal processor (DSP), and any suitable processor, controller, microcontroller, etc. Processor 51 performs the various methods and processes described above, such as methods for evaluating driving behavior.

[0202] In some embodiments, the driving behavior evaluation method may be implemented as a computer program tangibly contained in a computer-readable storage medium, such as storage unit 58. In some embodiments, part or all of the computer program may be loaded and / or installed on electronic device 50 via ROM 52 and / or communication unit 59. When the computer program is loaded into RAM 53 and executed by processor 51, one or more steps of the driving behavior evaluation method described above may be performed. Alternatively, in other embodiments, processor 51 may be configured to perform the driving behavior evaluation method by any other suitable means (e.g., by means of firmware).

[0203] Various embodiments of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field-programmable gate arrays (FPGAs), application-specific integrated circuits (ASICs), application-specific standard products (ASSPs), systems-on-a-chip (SoCs), complex programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various embodiments may include implementations in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which may be a dedicated or general-purpose programmable processor, capable of receiving data and instructions from a storage system, at least one input device, and at least one output device, and transmitting data and instructions to the storage system, the at least one input device, and the at least one output device.

[0204] Computer programs used to implement the methods of the present invention may be written in any combination of one or more programming languages. These computer programs may be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device, such that when executed by the processor, the computer programs cause the functions / operations specified in the flowcharts and / or block diagrams to be performed. The computer programs may be executed entirely on a machine, partially on a machine, or as a standalone software package, partially on a machine and partially on a remote machine, or entirely on a remote machine or server.

[0205] In the context of this invention, a computer-readable storage medium can be a tangible medium that may contain or store a computer program for use by or in conjunction with an instruction execution system, apparatus, or device. A computer-readable storage medium may include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination thereof. Alternatively, a computer-readable storage medium may be a machine-readable signal medium. More specific examples of machine-readable storage media include electrical connections based on one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fibers, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination thereof.

[0206] To provide interaction with a user, the systems and techniques described herein can be implemented on an electronic device having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and pointing device (e.g., a mouse or trackball) through which the user provides input to the electronic device. Other types of devices can also be used to provide interaction with the user; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including sound input, voice input, or tactile input).

[0207] The systems and technologies described herein can be implemented in computing systems that include backend components (e.g., as data servers), or computing systems that include middleware components (e.g., application servers), or computing systems that include frontend components (e.g., user computers with graphical user interfaces or web browsers through which users can interact with implementations of the systems and technologies described herein), or any combination of such backend, middleware, or frontend components. The components of the system can be interconnected via digital data communication of any form or medium (e.g., communication networks). Examples of communication networks include local area networks (LANs), wide area networks (WANs), blockchain networks, and the Internet.

[0208] A computing system can include clients and servers. Clients and servers are generally located far apart and typically interact through communication networks. The client-server relationship is created by computer programs running on the respective computers and having a client-server relationship with each other. The server can be a cloud server, also known as a cloud computing server or cloud host, which is a hosting product within the cloud computing service system to address the shortcomings of traditional physical hosts and VPS services, such as high management difficulty and weak business scalability.

[0209] It should be understood that the various forms of processes shown above can be used, with steps reordered, added, or deleted. For example, the steps described in this invention can be executed in parallel, sequentially, or in different orders, as long as the desired result of the technical solution of this invention can be achieved, and this is not limited herein.

[0210] The specific embodiments described above do not constitute a limitation on the scope of protection of this invention. Those skilled in the art should understand that various modifications, combinations, sub-combinations, and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of this invention should be included within the scope of protection of this invention.

Claims

1. A method of evaluating driving behavior, characterized by, The method comprises the following steps: acquiring at least two candidate trajectory points generated by a target vehicle within a target time period, and determining a corresponding candidate direction angle of the target vehicle at each candidate trajectory point; wherein the candidate direction angle refers to a corresponding direction angle of the target vehicle at each candidate trajectory point, and the direction angle refers to an included angle between a direction line of a driving direction of the target vehicle and a north-south direction; determining an auxiliary trajectory point from each candidate trajectory point according to a corresponding candidate direction angle of adjacent candidate trajectory points of the target vehicle; wherein the auxiliary trajectory point is a candidate trajectory point corresponding to a turning phenomenon of the target vehicle; taking a preset time period before a collection time of each auxiliary trajectory point as a corresponding candidate detection time period of each auxiliary trajectory point, and determining a target trajectory point from each auxiliary trajectory point according to an average driving speed of the target vehicle within each candidate detection time period; wherein the target trajectory point is an auxiliary trajectory point corresponding to a target detection time period, and the target detection time period is a candidate detection time period in which the average driving speed of the target vehicle is less than a speed threshold; evaluating a driving behavior generated by a driver of the target vehicle within the target time period according to a target trajectory point quantity of the target trajectory point.

2. The method of claim 1, wherein, The method comprises the following steps: determining a longitude difference value and a latitude difference value between adjacent candidate trajectory points according to a trajectory point longitude and a trajectory point latitude corresponding to each candidate trajectory point, respectively; determining a corresponding candidate direction angle of the target vehicle at each candidate trajectory point according to the longitude difference value and the latitude difference value.

3. The method of claim 2, wherein, The method comprises the following steps: determining the corresponding candidate direction angle of the target vehicle at each candidate trajectory point by using the following formula: ； wherein, represents a candidate direction angle corresponding to the target vehicle at any candidate trajectory point, represents the difference in longitude between the candidate trajectory point and a preceding trajectory point, represents the difference in latitude between the candidate trajectory point and the preceding trajectory point, the preceding trajectory point being a candidate trajectory point adjacent to the candidate trajectory point and collected at an earlier time than the candidate trajectory point.

4. The method of claim 1, wherein, The method comprises the following steps: determining a direction angle difference value between a candidate trajectory point and a preceding trajectory point according to the candidate direction angle of the candidate trajectory point and the candidate direction angle of the preceding trajectory point; wherein the preceding trajectory point is a candidate trajectory point adjacent to the candidate trajectory point and collected earlier than the candidate trajectory point; if an absolute value corresponding to the direction angle difference value is greater than a first difference threshold, the candidate trajectory point is taken as the auxiliary trajectory point.

5. The method of claim 1, wherein, The method comprises the following steps: determining a first quantity proportion of the target trajectory point relative to the auxiliary trajectory point according to the target trajectory point quantity of the target trajectory point and an auxiliary trajectory point quantity of the auxiliary trajectory point; evaluating the driving behavior generated by the driver of the target vehicle within the target time period according to the first quantity proportion.

6. A method of evaluating driving behavior, characterized by, The method comprises the following steps: obtaining at least two candidate trajectory points generated by a target vehicle in a target time period, and determining a candidate direction angle corresponding to each candidate trajectory point when the target vehicle is at the candidate trajectory point; wherein the candidate direction angle refers to a direction angle corresponding to each candidate trajectory point when the target vehicle is at the candidate trajectory point, and the direction angle refers to an included angle between a direction line of a driving direction of the target vehicle and a north-south direction; determining a direction angle difference between any candidate trajectory point and a preceding trajectory point according to the candidate direction angle of the candidate trajectory point and the candidate direction angle of the preceding trajectory point; wherein the preceding trajectory point is a candidate trajectory point adjacent to the candidate trajectory point and collected earlier than the candidate trajectory point; if an absolute value corresponding to the direction angle difference is greater than a second difference threshold, regarding the candidate trajectory point as an abnormal trajectory point; wherein the second difference threshold is greater than a first difference threshold, the first difference threshold represents a turning direction angle threshold adapted to a vehicle model of the target vehicle, and is used to determine whether the vehicle turns, and the abnormal trajectory point is a candidate trajectory point corresponding to a sharp turning phenomenon of the target vehicle; determining a second quantity proportion of the abnormal trajectory point relative to the auxiliary trajectory point according to an abnormal trajectory point quantity of the abnormal trajectory point and an auxiliary trajectory point quantity of the auxiliary trajectory point; evaluating a driving behavior of a driver of the target vehicle in the target time period according to the second quantity proportion.

7. A device for evaluating driving behavior, characterized in that, comprise: a candidate direction angle determination module, configured to obtain at least two candidate trajectory points generated by a target vehicle in a target time period, and determine a candidate direction angle corresponding to each candidate trajectory point when the target vehicle is at the candidate trajectory point; wherein the candidate direction angle refers to a direction angle corresponding to each candidate trajectory point when the target vehicle is at the candidate trajectory point, and the direction angle refers to an included angle between a direction line of a driving direction of the target vehicle and a north-south direction; an auxiliary trajectory point determination module, configured to determine auxiliary trajectory points from the candidate trajectory points according to candidate direction angles corresponding to the candidate trajectory points adjacent to the target vehicle; wherein the auxiliary trajectory points are candidate trajectory points corresponding to a turning phenomenon of the target vehicle; a target trajectory point determination module, configured to regard a preset time period before a collection time of each auxiliary trajectory point as a candidate detection time period corresponding to the auxiliary trajectory point, and determine target trajectory points from the auxiliary trajectory points according to an average driving speed of the target vehicle in each candidate detection time period; wherein the target trajectory points are auxiliary trajectory points corresponding to a target detection time period, and the target detection time period is a candidate detection time period in which the average driving speed of the target vehicle is less than a speed threshold; a driving behavior evaluation module, configured to evaluate a driving behavior of a driver of the target vehicle in the target time period according to a target trajectory point quantity of the target trajectory points.

8. An electronic device, comprising: The electronic device comprises: at least one processor; and a memory connected with the at least one processor in communication; wherein The memory stores a computer program executable by the at least one processor, and the computer program is executed by the at least one processor to enable the at least one processor to perform the driving behavior evaluation method of any one of claims 1-6.

9. A computer-readable storage medium, characterized in that, The computer readable storage medium stores computer instructions for causing a processor to perform the driving behavior evaluation method of any one of claims 1-6.

Images