Method and device for generating fleet safety portrait

Abstract

The present application provides a method and device for generating a fleet safety profile, the method comprising: obtaining a feature value corresponding to the features of the fleet within a first preset time; wherein the features of the fleet are generated by the vehicle networking hardware device of the fleet, including: vehicle driving features and driver behavior features; determining abnormal driver behavior features based on the feature values ​​corresponding to the acquired driver behavior features and the corresponding feature thresholds; generating a fleet safety profile of the fleet based on the feature values ​​corresponding to the acquired features of the fleet and the determined abnormal driver behavior features. The method can accurately construct a fleet safety profile in multiple dimensions.

Description

Technical Field

[0001] The present invention relates to the field of information processing technology, and in particular to a method and device for generating a vehicle fleet safety portrait. Background Art

[0002] Existing vehicle safety is evaluated through vehicle trajectory monitoring technology, which takes the vehicle as the observation subject and evaluates vehicle safety through formal parameters such as trajectory.

[0003] Among the features currently collected by profiling technology, the trajectory recognition function is relatively single, and the construction of a fleet safety profile based on a single feature is not comprehensive and accurate enough. Summary of the invention

[0004] In view of this, the present application provides a method and device for generating a fleet safety portrait, which can accurately construct a fleet safety portrait in multiple dimensions.

[0005] To solve the above technical problems, the technical solution of this application is implemented as follows:

[0006] In one embodiment, a method for generating a fleet safety profile is provided, the method comprising:

[0007] Acquire a characteristic value corresponding to the characteristics of the fleet within a first preset time; wherein the characteristics of the fleet are generated by the vehicle networking hardware device of the fleet, including: vehicle driving characteristics and driver behavior characteristics;

[0008] Determine abnormal driver behavior characteristics according to the acquired characteristic values ​​corresponding to the driver behavior characteristics and the corresponding characteristic thresholds;

[0009] A fleet safety profile of the fleet is generated based on the acquired feature values ​​corresponding to the features of the fleet and the determined abnormal driver behavior features.

[0010] In another embodiment, a vehicle fleet safety portrait generation device is provided, the device comprising: an acquisition unit, a determination unit, and a generation unit;

[0011] The acquisition unit is used to acquire a characteristic value corresponding to the characteristics of the fleet within a first preset time; wherein the characteristics of the fleet are generated by the vehicle networking hardware device of the fleet, including: vehicle driving characteristics and driver behavior characteristics;

[0012] The determining unit is used to determine the abnormal driver behavior feature according to the feature value corresponding to the driver behavior feature acquired by the acquiring unit and the corresponding feature threshold;

[0013] The generating unit is used to generate a fleet safety portrait of the fleet based on the characteristic value of the fleet acquired by the acquiring unit and the abnormal driver behavior characteristics determined by the determining unit.

[0014] In another embodiment, an electronic device is provided, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the steps of the fleet safety portrait generation method when executing the program.

[0015] In another embodiment, a computer-readable storage medium is provided, on which a computer program is stored, and when the program is executed by a processor, the steps of the fleet safety portrait generation method are implemented.

[0016] As can be seen from the above technical solution, in the above embodiment, the fleet is taken as a unit, and the fleet characteristics (vehicle driving characteristics and driver behavior characteristics) are selected according to the static data and the dynamic data provided by the Internet of Vehicles platform, and the fleet portrait is constructed to locate high-risk factors. This solution can accurately construct a fleet safety portrait in multiple dimensions to improve the accuracy of monitoring the safety of the fleet. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative labor.

[0018] Figure 1 A schematic diagram of a process for obtaining a feature threshold in an embodiment of the present application;

[0019] Figure 2 This is a schematic diagram of the process of generating a fleet safety portrait in an embodiment of the present application;

[0020] Figure 3 A schematic diagram of a process for determining abnormal driver behavior characteristics in an embodiment of the present application;

[0021] Figure 4 A schematic diagram of a process for obtaining a safety index score of a fleet in an embodiment of the present application;

[0022] Figure 5 This is a schematic diagram of the structure of a vehicle fleet safety portrait generating device in an embodiment of the present application;

[0023] Figure 6 A schematic diagram of the physical structure of an electronic device provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0024] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0025] The terms "first", "second", "third", "fourth", etc. (if any) in the specification and claims of the present invention and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchangeable where appropriate, so that the embodiments of the present invention described herein can be implemented in an order other than those illustrated or described herein, for example. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions. For example, a process, method, system, product, or device that includes a series of steps or units is not necessarily limited to those steps or units that are clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products, or devices.

[0026] The technical solution of the present invention is described in detail with specific embodiments below. The following specific embodiments can be combined with each other, and the same or similar concepts or processes may not be described in detail in some embodiments.

[0027] The present application provides a fleet safety portrait generation method that can be applied to freight scenarios. Taking the fleet as a unit, the fleet characteristics (vehicle driving characteristics and driver behavior characteristics) are selected based on static data and dynamic data provided by the Internet of Vehicles platform, and a fleet portrait is constructed to locate high-risk factors. At the same time, a method for calculating the safety index score of the fleet is given, and the impact of high-risk factors on the safety of the fleet is quantified based on the safety index score. This provides an optimization direction for reducing safety accidents, simplifies management processes, and intuitively understands the characteristics of the fleet.

[0028] In the embodiment of the present application, the characteristics of the fleet that need to be considered include: vehicle driving characteristics and driver behavior characteristics;

[0029] Wherein, the vehicle driving characteristics are determined by vehicle parameters, including vehicle type and average speed;

[0030] Driver behavior characteristics include: closing eyes, making phone calls, smoking, yawning, occlusion deviation, pedestrian warning, lane deviation, close vehicle warning, front vehicle collision, and distraction; but are not limited to the above characteristics.

[0031] The characteristic values ​​corresponding to the driver behavior characteristics are: number of times of closing eyes, number of times of making phone calls, number of times of smoking, number of times of yawning, number of times of occlusion deviation, number of times of pedestrian warning, number of times of lane deviation, number of times of close vehicle distance warning, number of times of front vehicle collision and number of times of distraction.

[0032] The feature thresholds corresponding to the driver behavior characteristics are: eyes closing feature threshold, phone call feature threshold, smoking feature threshold, yawning feature threshold, occlusion offset feature threshold, pedestrian warning feature threshold, lane offset feature threshold, vehicle distance too close warning feature threshold, front vehicle collision feature threshold and attention distraction feature threshold.

[0033] The vehicles in the embodiments of the present application need to have the function of counting the characteristic values ​​corresponding to the vehicle driving characteristics and the driver's behavior characteristics, and reporting them to the Internet of Vehicles system through the network, or transmitting them to other networked devices. When implemented specifically, the vehicles in the fleet need to be equipped with Internet of Vehicles hardware devices to realize this function.

[0034] The hardware equipment of the Internet of Vehicles is a collection of positioning devices, sensors, processing devices and networking devices. It can locate vehicle location information, vehicle driving information, obtain driver behavior information through information analysis such as pictures, and transmit data through networking devices.

[0035] In the embodiment of the present application, it is necessary to obtain the feature threshold corresponding to each feature of the fleet. When obtaining the feature threshold, it can be obtained periodically or when needed. This is not limited in the embodiment of the present application.

[0036] Among them, the characteristic values ​​corresponding to the characteristics of the fleet are generated by the vehicle networking hardware equipment of the fleet; when the characteristic values ​​corresponding to the characteristics of the fleet need to be used for related processing, this application can obtain them from the vehicles of the fleet or from the vehicle networking system.

[0037] See also Figure 1 , Figure 1 This is a flow chart of obtaining feature thresholds in an embodiment of the present application. The specific steps are:

[0038] Step 101, obtaining characteristic values ​​corresponding to the driver behavior characteristics of all vehicles in the area corresponding to the fleet within a second preset time.

[0039] When obtaining the characteristic threshold corresponding to the driver behavior characteristic of a fleet, it is necessary to obtain the driver behavior information of all vehicles in the area where the fleet is located, that is, to obtain the number of times each vehicle closed its eyes, made phone calls, smoked, yawned, had an occlusion deviation, had a pedestrian warning, had a lane deviation, had a close vehicle distance warning, collided with the vehicle in front, and was distracted within the second preset time.

[0040] Step 102: Calculate the expected value of the corresponding driver behavior feature based on the acquired feature value.

[0041] The expected values ​​of multiple eigenvalues ​​can be calculated by simulating mathematical models such as an average algorithm, Poisson distribution, binomial distribution, and normal distribution, which is not limited in the embodiments of the present application.

[0042] Step 103: determining a characteristic threshold of the corresponding driver behavior characteristic according to the expected value of the driver behavior characteristic.

[0043] In specific settings, the expected value can be used as the corresponding feature threshold, or the expected value can be multiplied by an empirical coefficient to correct data fluctuations, and the expected value multiplied by the empirical coefficient can be used as the corresponding feature threshold. The expectation can be the average value of the currently acquired feature values, or the weighted sum of the average value of the currently acquired feature values ​​and the average value acquired historically.

[0044] So far, a set of feature thresholds is obtained: {M1, M2, ..., M 10};

[0045] In order to prevent different feature thresholds from being in the same dimension and affecting the calculation of the overall data, the currently acquired feature thresholds are normalized in the embodiment of the present application:

[0046]

[0047] Among them, M i ' is the feature threshold M i Normalized feature threshold; M min is the minimum value among the feature thresholds in this group, M max is the maximum value among the feature thresholds in this group.

[0048] Then the normalized feature threshold is {M1', M2', ..., M 10 '}.

[0049] In the specific implementation, if the dimensional difference between the maximum value and the minimum value is too large, you can add a 0 and a large number feature threshold. The large number feature value is N times the maximum value in the current set of feature thresholds, and N is an integer greater than 1; then normalize and determine the normalized feature threshold as the feature threshold to be set. This implementation can avoid the constant corresponding attributes of the minimum and maximum values ​​in the original data set after data normalization, resulting in the highest frequency and lowest frequency events cannot be marked with features.

[0050] At this point, the feature thresholds of all dynamic features are obtained.

[0051] The following describes in detail the process of generating a fleet safety portrait in an embodiment of the present application in conjunction with the accompanying drawings.

[0052] Embodiment 1

[0053] See also Figure 2 , Figure 2 This is a schematic diagram of the fleet safety portrait generation process in the embodiment of this application. The specific steps are:

[0054] Step 201, obtaining characteristic values ​​corresponding to the characteristics of the fleet within a first preset time; wherein the characteristics of the fleet are generated by the vehicle networking hardware devices of the fleet, including: vehicle driving characteristics and driver behavior characteristics.

[0055] The characteristic value corresponding to the vehicle driving characteristic here is the average driving speed of a single vehicle.

[0056] First, the average speed of each vehicle in the fleet is obtained. If the average speed is not obtained, the average speed of the vehicle is set according to the type of vehicle and the historical average speed.

[0057] Secondly, calculate the average speed of each vehicle in the fleet;

[0058] The ratio of the sum of the average speeds of all vehicles in the fleet to the number of vehicles is taken as the average single-vehicle speed of the fleet;

[0059] If there are different types of vehicles in the fleet, the average speed of each vehicle is calculated for each type of vehicle.

[0060] Here, 10 driver behavior characteristics are taken as an example, which respectively obtain the number of times the entire fleet closes eyes, makes phone calls, smokes, yawns, has occlusions and deviations, has pedestrian warnings, has lane deviations, has close vehicle warnings, has front vehicle collisions, and has been distracted within the first preset time.

[0061] The first preset time may be the same as or different from the second preset time, and the starting point of the second preset time does not exceed the starting point of the first preset time.

[0062] Step 202: determining abnormal driver behavior characteristics according to the acquired characteristic values ​​corresponding to the driver behavior characteristics and the corresponding characteristic thresholds.

[0063] The specific implementation of this step can be found in Figure 3 , Figure 3 This is a flow chart of determining abnormal driver behavior characteristics in an embodiment of the present application. The specific steps are:

[0064] Step 301, obtaining the number of times each vehicle in the fleet closes its eyes, makes phone calls, smokes, yawns, deflects from an obstruction, warns of pedestrians, deflects from lanes, warns of close vehicle distances, collides with vehicles ahead, and distracts.

[0065] Step 302, calculate the average number of times the vehicle closes its eyes, the average number of times the vehicle makes phone calls, the average number of times the vehicle smokes, the average number of times the vehicle yawns, the average number of times the vehicle is blocked and deviated, the average number of times the vehicle has pedestrian warnings, the average number of times the vehicle has lane deviations, the average number of times the vehicle is too close to the vehicle warning, the average number of times the vehicle has collided with the vehicle in front, and the average number of times the vehicle has been distracted.

[0066] Among them, the average number of closed eyes of a single vehicle N1 is the ratio of the sum of the closed eyes of all vehicles in the fleet to the total number of vehicles;

[0067] The average number of phone calls per vehicle, N2, is the ratio of the sum of the number of phone calls of all vehicles in the fleet to the total number of vehicles;

[0068] The average number of smoking times per vehicle, N3, is the ratio of the sum of the number of smoking times of all vehicles in the fleet to the total number of vehicles;

[0069] The average number of yawns per vehicle, N4, is the ratio of the sum of the yawns of all vehicles in the fleet to the total number of vehicles;

[0070] The average number of occlusion offsets for a single vehicle, N5, is the ratio of the sum of the occlusion offsets for all vehicles in the fleet to the total number of vehicles;

[0071] The average number of pedestrian warnings per vehicle, N6, is the ratio of the sum of the pedestrian warnings of all vehicles in the fleet to the total number of vehicles;

[0072] The average number of lane deviations per vehicle, N7, is the ratio of the sum of the lane deviations of all vehicles in the fleet to the total number of vehicles;

[0073] The average number of short-distance warnings for a single vehicle, N8, is the ratio of the sum of the short-distance warnings for all vehicles in the fleet to the total number of vehicles;

[0074] The average number of front-vehicle collisions per vehicle, N9, is the ratio of the sum of the front-vehicle collisions of all vehicles in the fleet to the total number of vehicles;

[0075] The average number of distraction times for a single vehicle, N10, is the ratio of the sum of the distraction times of all vehicles in the fleet to the total number of vehicles.

[0076] Step 303, determine whether the average number of eye closure times N1 is greater than the eye closure times threshold M1, if yes, determine that the eye closure times are abnormal features; otherwise, determine that the eye closure times are not abnormal features. End this process.

[0077] If the number of eye-closing times is determined to be an abnormal feature, it is determined that the fleet has an eye-closing safety problem; otherwise, it is determined that the fleet does not have an eye-closing safety problem.

[0078] Step 304, determine whether the average number of phone calls per vehicle N2 is greater than the threshold number of phone calls M2, if yes, determine that the number of phone calls is an abnormal feature; otherwise, determine that the number of phone calls is not an abnormal feature. End this process.

[0079] If the number of phone calls is determined to be an abnormal feature, it is determined that the fleet has a phone call safety problem; otherwise, it is determined that the fleet does not have a phone call safety problem.

[0080] Step 305, determine whether the average number of times N3 of smoking per vehicle is greater than the threshold number of times M3 of smoking, if yes, determine that the number of times of smoking is an abnormal feature; otherwise, determine that the number of times of smoking is not an abnormal feature. End this process.

[0081] If the number of smoking times is determined to be an abnormal feature, it is determined that the fleet has a smoking safety problem; otherwise, it is determined that the fleet does not have a smoking safety problem.

[0082] Step 306, determine whether the average number of yawns per bicycle N4 is greater than the yawn number threshold M4, if yes, determine that the yawn number is an abnormal feature; otherwise, determine that the yawn number is not an abnormal feature. End this process.

[0083] If the number of yawning times is determined to be an abnormal feature, it is determined that the fleet has a yawning safety problem; otherwise, it is determined that the fleet does not have a yawning safety problem.

[0084] Step 307, determine whether the average number of single-vehicle occlusion offsets N5 is greater than the yawning number threshold M5, if yes, determine that the occlusion offsets are abnormal features; otherwise, determine that the occlusion offsets are not abnormal features. End this process.

[0085] The number of occlusion offsets is determined to be an abnormal feature, which means that the fleet is deemed to have an occlusion offset safety problem; otherwise, the fleet is deemed not to have an occlusion offset safety problem.

[0086] Step 308, determine whether the average number of single-vehicle pedestrian warning times N6 is greater than the pedestrian warning times threshold M6, if yes, determine that the pedestrian warning times are abnormal features; otherwise, determine that the pedestrian warning times are not abnormal features. End this process.

[0087] If the number of pedestrian warnings is determined to be an abnormal feature, it is determined that the fleet has a pedestrian warning safety problem; otherwise, it is determined that the fleet does not have a pedestrian warning safety problem.

[0088] Step 309, determine whether the average lane deviation times N7 of a single vehicle is greater than the lane deviation times threshold M7, if yes, determine that the lane deviation times are abnormal features; otherwise, determine that the lane deviation times are not abnormal features. End this process.

[0089] If the number of lane deviations is determined to be an abnormal feature, it is determined that the fleet has a lane deviation safety problem; otherwise, it is determined that the fleet does not have a lane deviation safety problem.

[0090] Step 310, determine whether the average number of short distance warnings per vehicle N8 is greater than the short distance warning threshold M8, if yes, determine that the short distance warning is an abnormal feature; otherwise, determine that the short distance warning is not an abnormal feature. End this process.

[0091] The number of close-distance warnings is determined to be an abnormal feature, which means that the fleet is deemed to have a close-distance warning safety problem; otherwise, the fleet is deemed not to have a close-distance warning safety problem.

[0092] Step 311, determine whether the average number of front vehicle collisions per vehicle N9 is greater than the front vehicle collision number threshold M9, if yes, determine that the front vehicle collision number is an abnormal feature; otherwise, determine that the front vehicle collision number is not an abnormal feature. End this process.

[0093] If the number of front vehicle collisions is determined to be an abnormal feature, it is determined that the fleet has a front vehicle collision safety problem; otherwise, it is determined that the fleet does not have a front vehicle collision safety problem.

[0094] Step 312, determine whether the average number of distraction times N10 of a bicycle is greater than the distraction times threshold M9, if yes, determine that the distraction times are abnormal features; otherwise, determine that the distraction times are not abnormal features.

[0095] If the number of distraction incidents is determined to be an abnormal feature, the fleet is deemed to have a distraction safety problem; otherwise, the fleet is deemed not to have a distraction safety problem.

[0096] Step 203: Generate a fleet safety profile of the fleet based on the acquired feature values ​​corresponding to the features of the fleet and the determined abnormal driver behavior features.

[0097] The data information in the fleet safety profile generated for the fleet at least includes vehicle driving characteristics and abnormal driver behavior characteristics, and the abnormal driver behavior characteristics are marked;

[0098] The form of generating the fleet safety portrait of the fleet is not limited in the embodiment of the present application, such as graphic distribution, table, etc.

[0099] In specific implementation, all vehicle driving characteristics and driver behavior characteristics, as well as corresponding characteristics, can also generate a fleet safety profile for the fleet, and indicate abnormal driver behavior characteristics.

[0100] In this embodiment, the fleet is taken as a unit, and the fleet characteristics (vehicle driving characteristics and driver behavior characteristics) are selected according to the static data (vehicle driving data) and the dynamic data (driver behavior data) provided by the Internet of Vehicles platform, and a fleet portrait is constructed to locate high-risk factors. This solution can accurately construct a fleet safety portrait in multiple dimensions to improve the accuracy and timeliness of fleet safety monitoring.

[0101] In the embodiments of the present application, a fleet safety portrait may be generated periodically, or when needed, or a combination of the two methods, which is not limited in the embodiments of the present application.

[0102] Embodiment 2

[0103] See also Figure 4 , Figure 4 This is a schematic diagram of the process of obtaining the safety index score of a fleet in an embodiment of the present application. The specific steps are:

[0104] Step 401, obtaining characteristic values ​​corresponding to the characteristics of the fleet within a first preset time; wherein the characteristics of the fleet are generated by the vehicle networking hardware devices of the fleet, including: vehicle driving characteristics and driver behavior characteristics.

[0105] The characteristic value corresponding to the vehicle driving characteristic here is the average driving speed of a single vehicle.

[0106] First, the average speed of each vehicle in the fleet is obtained. If the average speed is not obtained, the average speed of the vehicle is set according to the type of vehicle and the historical average speed.

[0107] Secondly, calculate the average speed of each vehicle in the fleet;

[0108] The ratio of the sum of the average speeds of all vehicles in the fleet to the number of vehicles is taken as the average single-vehicle speed of the fleet;

[0109] If there are different types of vehicles in the fleet, the average speed of each vehicle is calculated for each type of vehicle.

[0110] Here, 10 driver behavior characteristics are taken as an example, which respectively obtain the number of times the entire fleet closes eyes, makes phone calls, smokes, yawns, has occlusions and deviations, has pedestrian warnings, has lane deviations, has close vehicle warnings, has front vehicle collisions, and has been distracted within the first preset time.

[0111] The first preset time may be the same as or different from the second preset time, and the starting point of the second preset time does not exceed the starting point of the first preset time.

[0112] Step 402, determining abnormal driver behavior characteristics according to the acquired characteristic values ​​corresponding to the driver behavior characteristics and the corresponding characteristic thresholds.

[0113] Step 403 , determining the level corresponding to the exposure rate level and the level corresponding to the controllability level according to the characteristic value corresponding to the abnormal driver behavior characteristic.

[0114] There are four levels corresponding to the exposure rate level, which are arranged in order from low to high, namely: first-level exposure rate level, second-level exposure rate level, third-level exposure rate level and fourth-level exposure level; the first-level exposure rate level is an extremely low probability level, the second-level exposure rate level is a low probability level, the third-level exposure level is a medium probability level; the fourth-level exposure level is a high probability level.

[0115] The controllability level corresponds to four levels of controllability, which are arranged in order of uncontrollability from low to high, namely: first level controllability level, second level controllability level, third level controllability level and fourth level controllability level. The first level controllability level is the fully controllable level, the second level controllability level is the simple controllability level, the third level controllability level is the general controllability level, and the fourth level controllability level is the very difficult to control level.

[0116] In this embodiment, it is taken as an example that the controllability level and the exposure rate level correspond to four levels respectively. In specific implementation, the number of levels corresponding to each level can be flexibly set according to the actual application scenario.

[0117] Step 404: determine the level corresponding to the severity level according to the characteristic value corresponding to the vehicle driving characteristic.

[0118] The severity level corresponds to four levels, which are arranged in order from low to high severity, namely: first severity level, second severity level, third severity level and fourth severity level; the first severity level is no injury level S0, the second severity level is mild and moderate injury level S1; the third severity level is serious injury level S2, and the fourth severity level is fatal injury level S3.

[0119] In this embodiment, it is taken as an example that the severity levels correspond to four levels respectively. In specific implementation, the number of levels corresponding to the severity levels can be flexibly set according to the actual application scenario.

[0120] Step 405 , calculate the weight value of the abnormal driver behavior feature according to the risk coefficient of the level corresponding to the determined exposure level, the risk coefficient of the level corresponding to the controllability level, and the risk coefficient of the level corresponding to the severity level.

[0121] Four levels of risk factors corresponding to the exposure rate level, controllability level and severity level are preset:

[0122] The risk factors are set for the four levels corresponding to the severity level, and the risk factors corresponding to the first severity level to the fourth severity level decrease in sequence;

[0123] The risk coefficients are set for the four levels corresponding to the exposure rate level, and the risk coefficients corresponding to the first exposure rate level to the fourth exposure rate level decrease in sequence;

[0124] Risk factors are set for the four levels corresponding to the controllability levels, and the risk factors corresponding to the first controllability level to the fourth controllability level decrease in sequence.

[0125] Specifically, the risk factors corresponding to the first severity level to the fourth severity level can be set to: 1, 0.8, 0.6, 0.4;

[0126] The risk factors corresponding to the first to fourth exposure levels can be set as: 1, 0.8, 0.6, 0.4;

[0127] The risk factors corresponding to the first controllability level to the fourth controllability level can be set to 1, 0.8, 0.6, and 0.4 respectively.

[0128] The above setting is only an example, and the specific implementation is not limited to the above setting of risk coefficient.

[0129] In a specific implementation, a corresponding speed interval is set for each level of severity to determine the severity level corresponding to the average speed of a single vehicle, such as the speed interval defined by S0 is (0, 0], the speed interval defined by S1 is (0, 20], the speed interval defined by S2 is (20, 60]; the speed interval defined by S3 is (60, +∞), and the specific implementation is not limited to the above settings.

[0130] When each driver behavior feature is set as an abnormal feature, the corresponding exposure rate level and controllability level may be specifically set as follows, but are not limited to the following settings:

[0131] The closed-eye feature corresponds to the fourth level of exposure rate and the third level of controllability;

[0132] The calling feature corresponds to the second level exposure rate level and the second level controllability level;

[0133] The smoking characteristics correspond to the third level of exposure rate and the third level of controllability;

[0134] The yawning feature corresponds to the third level of exposure rate and the fourth level of controllability;

[0135] The occlusion offset feature corresponds to the second level exposure rate level and the second level controllability level;

[0136] The pedestrian warning features correspond to the second level exposure rate level and the second level controllability level;

[0137] The lane deviation feature corresponds to the fourth level exposure rate level and the second level controllability level;

[0138] The vehicle-to-vehicle distance warning feature corresponds to the fourth level exposure rate level and the second level controllability level;

[0139] The front vehicle collision characteristics correspond to the second level exposure rate level and the second level controllability level;

[0140] The distraction feature corresponds to the third level of exposure rate and the fourth level of controllability.

[0141] In this step, the weight value of the abnormal driver behavior feature is calculated according to the risk coefficient of the level corresponding to the determined exposure level, the risk coefficient of the level corresponding to the controllability level, and the risk coefficient of the level corresponding to the severity level, including:

[0142] The weight value W of abnormal driver behavior characteristics is calculated by the following formula: i :

[0143] W i =1-W S ×W E ×W C ;

[0144] Among them, W S W is the risk factor of the level corresponding to the severity level; E is the risk factor of the level corresponding to the exposure level, W C W is the risk factor of the level corresponding to the controllability level; i is the weight value of the i-th abnormal driver behavior feature.

[0145] Step 406 , calculating the safety index score of the fleet according to the weight value of the abnormal driver behavior characteristics.

[0146] Among them, the higher the safety index score is, the greater the safety hazard of the fleet is.

[0147] In this step, the safety index score of the fleet is calculated based on the weight value of the abnormal driver behavior characteristics, including:

[0148] The weight value corresponding to the abnormal driver behavior feature is multiplied by the corresponding preset feature basic score, and the sum is taken as the fleet's safety index score.

[0149] In specific implementation, the fleet may include one or more types of vehicle models. If the fleet includes multiple types of vehicle models, then when calculating the weight value of the abnormal driver behavior characteristics based on the risk coefficient of the level corresponding to the determined exposure level, the risk coefficient of the level corresponding to the controllability level, and the risk coefficient of the level corresponding to the severity level, the weight values ​​of the abnormal driver behavior characteristics corresponding to different vehicle models are calculated respectively; when calculating the safety index score of the fleet based on the weight values ​​of the abnormal driver behavior characteristics, the product of the weight value corresponding to the abnormal driver behavior characteristics of each vehicle model and the corresponding preset feature basic score is calculated respectively, and the sum of all the calculated products is taken as the safety index score of the fleet.

[0150] In the specific implementation, it is possible to introduce Boolean quantities and calculate the fleet safety index score through the following formula:

[0151]

[0152] Among them, when the behavior characteristics of the i-th driver are abnormal, bool i is 1; otherwise it is 0; is the proportion of vehicle types in the fleet; I is the total number of driver behavior characteristics; b i The base score for the preset feature.

[0153] In specific implementation, the preset feature basic scores set for different driver behavior characteristics can be the same or different. The specific settings can be implemented according to actual needs and are not limited in this embodiment of the present application.

[0154] This embodiment provides a method for calculating the safety index score of a fleet, and quantifies the impact of high-risk factors on the safety of the fleet based on the safety index score, so as to provide an optimization direction for reducing safety accidents, simplify the management process, and intuitively understand the characteristics of the fleet.

[0155] In the embodiment of the present application, the safety index score of the fleet can be calculated periodically, or the safety index score can be generated when needed, or the two methods can be combined, which is not limited in the embodiment of the present application.

[0156] Embodiment 3

[0157] In this embodiment, a specific process of generating a fleet safety profile and a safety index score is given in conjunction with a specific embodiment.

[0158] A freight company A has 10 fleets in a certain area. Each fleet has 10 trucks, all of which are equipped with Internet of Vehicles hardware devices. The hardware devices collect vehicle driving information and driver alarm behavior information and upload them to the Internet of Vehicles system.

[0159] The average data of the characteristic values ​​of the driver behavior characteristics of the 100 vehicles within the second preset time (one week) can be calculated as <7.00, 2.80, 8.94, 8.80, 6.47, 6.67, 57.86, 62.13, 2.27, 4.58>. After normalization, <0.080.01 0.11 0.11 0.07 0.07 0.93 1 0 0.04> is obtained. Assuming the threshold coefficient θ i All of them are 1, and the feature threshold is: <0.08 0.01 0.11 0.11 0.07 0.07 0.93 1 0 0.04>. It is judged that the difference in numerical magnitude is not large, and no empty feature variable is introduced.

[0160] Take fleet A as an example. The 10 vehicles in the fleet are 8 high-speed trains with an average speed of 80 and 2 box-type heavy trucks with an average speed of 50.

[0161] Assume that the average values ​​calculated by obtaining the characteristic values ​​corresponding to the driver behavior characteristics of the fleet are: average number of eye closures: 9.50 times, average number of phone calls: 0.75 times, average number of smoking: 6.54 times, average number of yawns: 6.82 times, average number of occlusion offsets: 4.43 times, average number of pedestrian warnings: 4.57 times, average number of lane deviations: 53.67 times, average number of close vehicle warnings: 61.80 times, average number of front vehicle collisions: 2.17 times, and average number of distractions: 6.59 times.

[0162] Thus, the average values ​​of the characteristic values ​​of the driver behavior characteristics of the fleet are obtained: 9.50, 0.75, 6.54, 6.82, 4.43, 4.57, 53.67, 61.80, 2.17, 6.59>, where X max is 61.80, X min is 0.75, and after normalization we get <0.150 0.11 0.11 0.07 0.07 0.88 1 0.04 0.11>.

[0163] According to the judgment rules, driver behavior characteristics that are greater than the characteristic threshold are abnormal driver behavior characteristics, including: eyes closing characteristics, front vehicle collision characteristics, and attention distraction characteristics.

[0164] A fleet safety portrait is generated based on abnormal driver behavior characteristics, vehicle driving characteristics of the fleet, and corresponding feature values. There is no limit on the form of the safety portrait, such as word cloud portrait, icon portrait, etc.

[0165] The closed-eye feature corresponds to the fourth-level exposure rate level and the third-level controllability level. The weight of the closed-eye feature of the high-speed train is: 1-0.4×0.6×0.4=0.904; the weight of the closed-eye feature of the box-type heavy truck is 1-0.6×0.6×0.4=0.856.

[0166] The front vehicle collision characteristics correspond to the second level exposure rate level and the second level controllability level. The weight of the front vehicle collision characteristics of the high-speed train is: 1-0.4×0.8×0.8=0.744; the weight of the front vehicle collision characteristics of the box-type heavy truck is 1-0.6×0.8×0.8=0.616.

[0167] The attention distraction feature corresponds to the third level exposure rate level and the fourth level controllability level. The weight of the attention distraction feature of the high-speed train is: 1-0.4×0.6×0.4=0.904; the weight of the attention distraction feature of the box-type heavy truck is 1-0.6×0.6×0.4=0.856.

[0168] The safety index score of the fleet is calculated as:

[0169] 10×0.8×0.904+10×0.2×0.856+10×0.8×0.904+10×0.2×0.856+10×0.8×0.744+10×0.2×0.616=21.988.

[0170] Here, when calculating, the preset feature basic score set for each abnormal driver behavior feature is taken as 10. In the specific implementation, it can be set according to the actual magnitude of the measurement score.

[0171] Based on the same level of comparison, the higher the fleet safety index score, the greater the safety risks of the fleet.

[0172] Based on the same inventive concept, the present application also provides a fleet safety portrait generation device. Figure 5 , Figure 5 This is a schematic diagram of the structure of a vehicle fleet safety portrait generation device in an embodiment of the present application. The device includes: an acquisition unit 501, a determination unit 502 and a generation unit 503;

[0173] The acquisition unit 501 is used to acquire a characteristic value corresponding to the characteristics of the fleet within a first preset time; wherein the characteristics of the fleet are generated by the vehicle networking hardware device of the fleet, including: vehicle driving characteristics and driver behavior characteristics;

[0174] A determination unit 502, configured to determine an abnormal driver behavior feature according to a feature value corresponding to the driver behavior feature acquired by the acquisition unit 501 and a corresponding feature threshold;

[0175] The generating unit 503 is used to generate a fleet safety portrait of the fleet based on the characteristic value of the fleet acquired by the acquiring unit 501 and the abnormal driver behavior characteristics determined by the determining unit 502.

[0176] In another embodiment, the apparatus further comprises: a computing unit 504;

[0177] The determination unit 502 is further used to determine the level corresponding to the exposure rate level and the level corresponding to the controllability level according to the characteristic value corresponding to the abnormal driver behavior characteristic; determine the level corresponding to the severity level according to the characteristic value corresponding to the vehicle driving characteristic;

[0178] The calculation unit 504 is further used to calculate the weight value of the abnormal driver behavior characteristics according to the risk coefficient of the level corresponding to the exposure level determined by the determination unit 502, the risk coefficient of the level corresponding to the controllability level, and the risk coefficient of the level corresponding to the severity level; calculate the safety index score of the fleet according to the weight value of the abnormal driver behavior characteristics; wherein, the higher the safety index score, the greater the safety hazard of the fleet.

[0179] In another embodiment,

[0180] The acquisition unit 501 is specifically used to obtain the characteristic threshold value corresponding to the driver behavior characteristic, including: obtaining the characteristic value corresponding to the driver behavior characteristic of all vehicles in the area corresponding to the fleet within a second preset time; calculating the expected value of the corresponding driver behavior characteristic based on the obtained characteristic value; and determining the characteristic threshold value of the corresponding driver behavior characteristic based on the expected value of the driver behavior characteristic.

[0181] In another embodiment,

[0182] The vehicle driving characteristics are the average driving speed of the vehicle; the driver behavior characteristics include: eye closing characteristics, phone call characteristics, smoking characteristics, yawning characteristics, occlusion deviation characteristics, pedestrian warning characteristics, lane deviation characteristics, vehicle distance warning characteristics, front vehicle collision characteristics and attention distraction characteristics;

[0183] The characteristic values ​​corresponding to the driver behavior characteristics are: number of times of closing eyes, number of times of making phone calls, number of times of smoking, number of times of yawning, number of times of occlusion deviation, number of times of pedestrian warning, number of times of lane deviation, number of times of too close distance warning, number of times of front vehicle collision and number of times of distraction;

[0184] The feature thresholds corresponding to the driver behavior characteristics are: eyes closing feature threshold, phone call feature threshold, smoking feature threshold, yawning feature threshold, occlusion offset feature threshold, pedestrian warning feature threshold, lane offset feature threshold, vehicle distance too close warning feature threshold, front vehicle collision feature threshold and attention distraction feature threshold.

[0185] In another embodiment,

[0186] The determination unit 502 is specifically configured to determine the abnormal driver behavior feature according to the acquired feature value corresponding to the driver behavior feature and the corresponding feature threshold, including:

[0187] If the number of eye closing times is greater than the eye closing feature threshold, the eye closing feature is determined to be an abnormal driver behavior feature;

[0188] If the number of phone calls is greater than the eye-closing feature threshold, the phone call feature is determined to be an abnormal driver behavior feature;

[0189] If the number of closed-eye smoking is greater than the closed-eye feature threshold, the smoking feature is determined to be an abnormal driver behavior feature;

[0190] If the number of yawning times is greater than the eye-closing feature threshold, the yawning feature is determined to be an abnormal driver behavior feature;

[0191] If the number of occlusion offsets is greater than the eye-closing feature threshold, the occlusion offset feature is determined to be an abnormal driver behavior feature;

[0192] If the number of pedestrian warnings is greater than the eye-closing feature threshold, the pedestrian warning feature is determined to be an abnormal driver behavior feature;

[0193] If the number of lane deviations is greater than the eye-closing feature threshold, the lane deviation feature is determined to be an abnormal driver behavior feature;

[0194] If the number of vehicle-to-vehicle distance warnings is greater than the eye-closing feature threshold, the vehicle-to-vehicle distance warning feature is determined to be an abnormal driver behavior feature;

[0195] If the number of front vehicle collisions is greater than the eye-closing feature threshold, the front vehicle collision feature is determined to be an abnormal driver behavior feature;

[0196] If the number of distraction events is greater than the eye-closing feature threshold, the distraction feature is determined to be an abnormal driver behavior feature.

[0197] In another embodiment,

[0198] The calculation unit 504 is specifically used to calculate the weight value of the abnormal driver behavior feature according to the risk coefficient of the level corresponding to the determined exposure level, the risk coefficient of the level corresponding to the controllability level, and the risk coefficient of the level corresponding to the severity level, including: calculating the weight value of the abnormal driver behavior feature by the following formula:

[0199] 1-W S ×W E ×W C ;

[0200] Among them, W SW is the risk factor of the level corresponding to the severity level; E is the risk factor of the level corresponding to the exposure level, W C is the risk factor of the level corresponding to the controllability level.

[0201] In another embodiment,

[0202] The calculation unit 504 is specifically configured to calculate the safety index score of the fleet according to the weight value of the abnormal driver behavior feature, including:

[0203] The weight value corresponding to the abnormal driver behavior feature is multiplied by the corresponding preset feature basic score, and the sum is taken as the fleet's safety index score.

[0204] In another embodiment, if the vehicle models of the fleet include multiple types, when calculating the weight value of the abnormal driver behavior characteristics according to the risk coefficient of the level corresponding to the determined exposure level, the risk coefficient of the level corresponding to the controllability level, and the risk coefficient of the level corresponding to the severity level, the weight values ​​of the abnormal driver behavior characteristics corresponding to different vehicle models are calculated respectively;

[0205] If the vehicle models of the fleet include multiple types, then when calculating the safety index score of the fleet based on the weight values ​​of the abnormal driver behavior characteristics, the product of the weight value corresponding to the abnormal driver behavior characteristics of each vehicle model and the corresponding preset feature basic score is calculated respectively, and the sum of all the calculated products is taken as the safety index score of the fleet.

[0206] The units in the above-mentioned embodiments may be integrated into one body or deployed separately; they may be combined into one unit or further divided into multiple sub-units.

[0207] In another embodiment, an electronic device is provided, including a memory, a processor, and a computer program stored in the memory and executable on the processor, and the processor implements the steps of the method for generating a fleet safety portrait when executing the program.

[0208] In another embodiment, a computer-readable storage medium is provided, on which computer instructions are stored. When the instructions are executed by a processor, the steps in the method for generating a fleet safety portrait can be implemented.

[0209] Figure 6 Schematic diagram of the physical structure of an electronic device provided by an embodiment of the present invention. Figure 6As shown, the electronic device may include: a processor (Processor) 610, a communication interface (Communications Interface) 620, a memory (Memory) 630 and a communication bus 640, wherein the processor 610, the communication interface 620, and the memory 630 communicate with each other through the communication bus 640. The processor 610 may call the logic instructions in the memory 630 to execute the following method:

[0210] Obtaining feature values ​​corresponding to features of the fleet within a first preset time; the features include vehicle driving features and driver behavior features;

[0211] Determine abnormal driver behavior characteristics according to the acquired characteristic values ​​corresponding to the driver behavior characteristics and the corresponding characteristic thresholds;

[0212] A fleet safety profile of the fleet is generated based on the acquired feature values ​​corresponding to the features of the fleet and the determined abnormal driver behavior features.

[0213] In addition, the logic instructions in the above-mentioned memory 630 can be implemented in the form of a software functional unit and can be stored in a computer-readable storage medium when it is sold or used as an independent product. Based on such an understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art or the part of the technical solution, can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including a number of instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the methods of each embodiment of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk and other media that can store program codes.

[0214] The device embodiments described above are merely illustrative, wherein the units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, i.e., they may be located in one place, or they may be distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the scheme of this embodiment. Those of ordinary skill in the art may understand and implement it without creative effort.

[0215] Through the description of the above implementation methods, those skilled in the art can clearly understand that each implementation method can be implemented by means of software plus a necessary general hardware platform, and of course, it can also be implemented by hardware. Based on this understanding, the above technical solution is essentially or the part that contributes to the prior art can be embodied in the form of a software product, and the computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, a disk, an optical disk, etc., including a number of instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods described in each embodiment or some parts of the embodiments.

[0216] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included in the scope of protection of the present invention.

Claims

1. A method for generating a fleet safety profile, characterized in that: The method comprises: Acquire a characteristic value corresponding to the characteristics of the fleet within a first preset time; wherein the characteristics of the fleet are generated by the vehicle networking hardware device of the fleet, including: vehicle driving characteristics and driver behavior characteristics; Determine abnormal driver behavior characteristics according to the acquired characteristic values ​​corresponding to the driver behavior characteristics and the corresponding characteristic thresholds; Generating a fleet safety profile of the fleet based on the acquired feature values ​​corresponding to the features of the fleet and the determined abnormal driver behavior features; Obtaining the characteristic threshold corresponding to the driver's behavior characteristic, including: Obtaining characteristic values ​​corresponding to the driver behavior characteristics of all vehicles in the area corresponding to the fleet within a second preset time; Calculate the expected value of the corresponding driver behavior feature according to the acquired feature value; Determining a characteristic threshold of a corresponding driver behavior characteristic according to an expected value of the driver behavior characteristic; the method further comprises: Determine the level corresponding to the exposure rate level and the level corresponding to the controllability level according to the characteristic value corresponding to the abnormal driver behavior characteristic; Determining a level corresponding to the severity level according to a characteristic value corresponding to the vehicle driving characteristic; Calculate a weight value of the abnormal driver behavior feature according to the risk factor of the level corresponding to the determined exposure level, the risk factor of the level corresponding to the controllability level, and the risk factor of the level corresponding to the severity level; Calculate the safety index score of the fleet according to the weight value of the abnormal driver behavior characteristics; wherein the higher the safety index score, the greater the safety hazard of the fleet; The weight value of the abnormal driver behavior feature is calculated according to the risk coefficient of the level corresponding to the determined exposure level, the risk coefficient of the level corresponding to the controllability level, and the risk coefficient of the level corresponding to the severity level, including: The weight value of abnormal driver behavior characteristics is calculated by the following formula: 1-W S ×W E ×W C ; Among them, W S W is the risk factor of the level corresponding to the severity level; E is the risk factor of the level corresponding to the exposure level, W C is the risk factor of the level corresponding to the controllability level; The calculation of the safety index score of the fleet according to the weight value of the abnormal driver behavior characteristics includes: The weight value corresponding to the abnormal driver behavior feature is multiplied by the corresponding preset feature basic score, and the sum is taken as the fleet's safety index score.

2. The method according to claim 1, characterized in that: The vehicle driving characteristics are the average driving speed of the vehicle; the driver behavior characteristics include: eye closing characteristics, phone call characteristics, smoking characteristics, yawning characteristics, occlusion deviation characteristics, pedestrian warning characteristics, lane deviation characteristics, vehicle distance warning characteristics, front vehicle collision characteristics and attention distraction characteristics; The characteristic values ​​corresponding to the driver behavior characteristics are: number of times of closing eyes, number of times of making phone calls, number of times of smoking, number of times of yawning, number of times of occlusion deviation, number of times of pedestrian warning, number of times of lane deviation, number of times of too close distance warning, number of times of front vehicle collision and number of times of distraction; The feature thresholds corresponding to the driver behavior characteristics are: eyes closing feature threshold, phone call feature threshold, smoking feature threshold, yawning feature threshold, occlusion offset feature threshold, pedestrian warning feature threshold, lane offset feature threshold, vehicle distance too close warning feature threshold, front vehicle collision feature threshold and attention distraction feature threshold.

3. The method according to claim 2, characterized in that The determining of abnormal driver behavior characteristics according to the acquired characteristic values ​​corresponding to the driver behavior characteristics and the corresponding characteristic thresholds includes: If the number of eye closing times is greater than the eye closing feature threshold, the eye closing feature is determined to be an abnormal driver behavior feature; If the number of phone calls is greater than the eye-closing feature threshold, the phone call feature is determined to be an abnormal driver behavior feature; If the number of closed-eye smoking is greater than the closed-eye feature threshold, the smoking feature is determined to be an abnormal driver behavior feature; If the number of yawning times is greater than the eye-closing feature threshold, the yawning feature is determined to be an abnormal driver behavior feature; If the number of occlusion offsets is greater than the eye-closing feature threshold, the occlusion offset feature is determined to be an abnormal driver behavior feature; If the number of pedestrian warnings is greater than the eye-closing feature threshold, the pedestrian warning feature is determined to be an abnormal driver behavior feature; If the number of lane deviations is greater than the eye-closing feature threshold, the lane deviation feature is determined to be an abnormal driver behavior feature; If the number of vehicle-to-vehicle distance warnings is greater than the eye-closing feature threshold, the vehicle-to-vehicle distance warning feature is determined to be an abnormal driver behavior feature; If the number of front vehicle collisions is greater than the eye-closing feature threshold, the front vehicle collision feature is determined to be an abnormal driver behavior feature; If the number of distraction events is greater than the eye-closing feature threshold, the distraction feature is determined to be an abnormal driver behavior feature.

4. The method according to claim 1, characterized in that: If the vehicle models of the fleet include multiple types, when calculating the weight value of the abnormal driver behavior characteristics according to the risk coefficient of the level corresponding to the determined exposure level, the risk coefficient of the level corresponding to the controllability level, and the risk coefficient of the level corresponding to the severity level, the weight values ​​of the abnormal driver behavior characteristics corresponding to different vehicle models are calculated respectively; If the vehicle models of the fleet include multiple types, then when calculating the safety index score of the fleet based on the weight values ​​of the abnormal driver behavior characteristics, the product of the weight value corresponding to the abnormal driver behavior characteristics of each vehicle model and the corresponding preset feature basic score is calculated respectively, and the sum of all the calculated products is taken as the safety index score of the fleet.

5. A vehicle fleet safety portrait generation device, characterized in that: The device comprises: an acquisition unit, a determination unit and a generation unit; The acquisition unit is used to acquire a characteristic value corresponding to the characteristics of the fleet within a first preset time; wherein the characteristics of the fleet are generated by the vehicle networking hardware device of the fleet, including: vehicle driving characteristics and driver behavior characteristics; The determining unit is used to determine the abnormal driver behavior feature according to the feature value corresponding to the driver behavior feature acquired by the acquiring unit and the corresponding feature threshold; The generating unit is configured to generate a fleet safety profile of the fleet based on the characteristic value of the fleet acquired by the acquiring unit and the abnormal driver behavior characteristics determined by the determining unit; The acquisition unit is specifically used to acquire the characteristic threshold value corresponding to the driver behavior characteristic, including: acquiring characteristic values ​​corresponding to the driver behavior characteristics of all vehicles in the area corresponding to the fleet within a second preset time; calculating the expected value of the corresponding driver behavior characteristic according to the acquired characteristic value; and determining the characteristic threshold value of the corresponding driver behavior characteristic according to the expected value of the driver behavior characteristic; The device further comprises: a computing unit; The determination unit is further used to determine the level corresponding to the exposure rate level and the level corresponding to the controllability level according to the characteristic value corresponding to the abnormal driver behavior characteristic; determine the level corresponding to the severity level according to the characteristic value corresponding to the vehicle driving characteristic; The calculation unit is further used to calculate the weight value of the abnormal driver behavior feature according to the risk coefficient of the level corresponding to the exposure level determined by the determination unit, the risk coefficient of the level corresponding to the controllability level, and the risk coefficient of the level corresponding to the severity level; calculate the safety index score of the fleet according to the weight value of the abnormal driver behavior feature; wherein the higher the safety index score, the greater the safety hazard of the fleet; The calculation unit is further used to calculate the weight value of the abnormal driver behavior feature by the following formula: 1-W S ×W E ×W C ; Among them, W S W is the risk factor of the level corresponding to the severity level; E is the risk factor of the level corresponding to the exposure level, W C is the risk factor of the level corresponding to the controllability level; The calculation unit is further used to sum the product of the weight value corresponding to the abnormal driver behavior feature and the corresponding preset feature basic score as the safety index score of the fleet.

6. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the program, the method according to any one of claims 1 to 4 is implemented.

7. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the program is executed by a processor, the method described in any one of claims 1 to 4 is implemented.

Images