CN107833464B - Driving behavior safety assessment method and storage medium - Google Patents

Abstract

The invention discloses a driving behavior safety assessment method. The method comprises: pre-storing road network data, the road network data including road descriptive data and intersection signal light descriptive data; The state data includes the traveler ID, travel time, geographic location, travel speed and travel acceleration; the travel state data is divided into intersection data and non-intersection data according to the distance of the traveler from the intersection; according to the non-intersection data, The corresponding road network data is used to evaluate the non-intersection driving behavior; the home socket driving behavior is evaluated according to the intersection data, the corresponding road network data and the real-time acquired intersection signal light status data; according to the aforementioned evaluation results, calculate Driving safety index, the present invention provides data support for optimal management of distribution service personnel.

Description

A driving behavior safety assessment method and storage medium

technical field

The invention relates to the technical field of data processing and analysis, in particular to a driving behavior safety evaluation method and a storage medium.

Background technique

With the continuous advancement of Internet technology, the distribution service industry has been greatly developed. At present, short-distance distribution business personnel mostly use electric bicycles, but also use motorcycles, small cars, and small trucks. Due to the characteristics of fast speed, low price, low energy consumption, and convenient riding, electric bicycles provide effective hardware support for the distribution service industry and are widely used. With the large-scale use of electric bicycles, the disadvantages of electric bicycles in traffic safety are becoming more and more obvious. Because electric bicycles are two-wheeled vehicles, there are certain instability in their own driving process, and the pursuit of speed by practitioners has led to high traffic safety risks. Therefore, it is necessary to evaluate the riding safety of electric bicycle riders, so as to be able to judge and evaluate the safety of electric bicycle drivers' driving behavior in real time and efficiently, and assist in the management of drivers and accident prevention.

In the current social research on the safety of electric bicycles, on the one hand, the structure of the electric bicycle is taken as the research object, and the safety evaluation is completed through the performance test of the electric bicycle; and the performance of electric vehicles. However, in the process of practical application, it is difficult to directly test the performance of electric bicycles, and it mainly depends on the manufacturers of electric bicycles.

There are existing methods for scoring the driving behavior of cars in the prior art, but they all rely on the professional sensors of the on-board equipment of the car to collect data, which makes the cost of the vehicle very high, and the collected data contains a lot of state information about the vehicle itself. The scoring process is very complicated and untimely.

Especially in the current context of sharing, there are many times when the two vehicles can be shared by multiple people, and it is also necessary to conduct a safety assessment of the driving behavior of different users.

Therefore, how to directly obtain data and evaluate driving behaviors reliably and efficiently based on the data is a technical problem that needs to be solved at present.

SUMMARY OF THE INVENTION

In view of the above-mentioned problems, the present invention has been proposed in order to provide a method that overcomes the above-mentioned problems or at least partially solves the above-mentioned problems.

One aspect of the present invention provides a driving behavior safety assessment method, the method comprising: pre-storing road network data, the road network data including road descriptive data and intersection signal descriptive data;

Acquiring driving status data, the driving status data includes the driver's ID, driving time, geographic location, driving speed and driving acceleration;

Divide the driving state data into intersection data and non-intersection data according to the distance of the traveler from the nearest intersection;

Evaluate the non-intersection driving behavior according to the non-intersection data and the corresponding road network data;

Evaluate the driving behavior at the intersection according to the intersection data, the corresponding road network data and the real-time obtained intersection signal light status data;

The driving safety index is calculated according to the aforementioned evaluation results.

Optionally, the method further includes:

The obtained geographic location information is matched with the pre-stored road network data to obtain the matched road latitude and longitude mapping points as the processed geographic location of the traveler.

Optionally, the driving state data is divided into intersection data and non-intersection data according to the distance of the traveler from the nearest intersection, specifically including:

Preset the first distance threshold Ld before the intersection, and the second distance threshold Lb after the intersection;

Calculate the distance between the geographic location of the traveler and the nearest intersection;

If the distance calculated before passing through the intersection is less than the threshold value Ld, or the distance calculated after passing through the intersection is less than the threshold value Lb, the driving state data corresponding to the geographic location of the traveler is divided into intersection data, Otherwise, it is classified as non-intersection data.

Optionally, the driving state data is divided into intersection data and non-intersection data according to the distance of the traveler from the intersection, specifically including:

Preset the first distance threshold Ld and the second distance threshold Ld1, where Ld>Ld1;

Calculate the distance between the geographic location of the traveler and the nearest intersection;

If the calculated distance is less than the threshold Ld, the driving state data corresponding to the geographic location of the traveler is divided into intersection data;

If the calculated distance is greater than the threshold value Ld1, the traveling state data corresponding to the geographic location of the traveler is classified as non-intersection data.

Optionally, the non-intersection driving behavior is evaluated according to the non-intersection data and corresponding road network data, specifically including:

The speed stability index is calculated based on the driving speed.

Optionally, the non-intersection driving behavior is evaluated according to the non-intersection data and corresponding road network data, specifically including:

The speed jerky index is calculated from the travel acceleration.

Optionally, the non-intersection driving behavior is evaluated according to the non-intersection data and corresponding road network data, specifically including:

Calculates a speed overspeed indicator based on driving speed and road descriptive data.

Optionally, evaluating the driving behavior at the intersection according to the intersection data, the corresponding road network data and the real-time acquired intersection signal light status data, specifically including:

According to the obtained matching vector between the geographic location of the driver and the road network data and the real-time acquisition of the red light cycle at the intersection, it is judged whether there is a red light running behavior.

Optionally, evaluating the driving behavior at the intersection according to the intersection data, the corresponding road network data and the real-time acquired intersection signal light status data, specifically including:

According to the driving acceleration at the intersection and the status data of the intersection signal lights obtained in real time, it is judged whether there is an acceleration driving behavior at the intersection.

Optionally, evaluating the driving behavior at the intersection according to the intersection data, the corresponding road network data and the real-time acquired intersection signal light status data, specifically including:

According to the obtained matching vector and acceleration vector between the geographic location of the driver and the road network data, it is judged whether there is a sharp turning behavior.

Optionally, the method further includes:

The intersection behavior index is calculated according to the judgment result.

Optionally, the step: calculate the driving safety index according to the foregoing evaluation result, which specifically includes:

For a single driving process, the driving safety index is calculated according to the weighting of each index.

Optionally, the step: calculate the driving safety index according to the foregoing evaluation result, which specifically includes:

For the multiple driving process, the single driving safety index is weighted according to the travel period to obtain the total driving safety index.

Optionally, the method includes the steps of: acquiring driving state data, and then further comprising: extracting valid driving state data from the acquired driving state data, specifically including filtering abnormal data and/or extracting data greater than a predetermined driving speed.

Optionally, the driving behavior safety evaluation method is an electric vehicle driving behavior safety evaluation method.

Optionally, the driving state data is obtained through a mobile terminal application.

The present invention provides a storage medium for storing a computer program for executing the aforementioned method.

The present invention provides a server comprising a memory, a processor and a computer program stored on the memory, the computer program implementing the steps of the aforementioned method when executed by the processor.

The present invention provides a handheld terminal, which includes a memory, a processor, and a computer program stored on the memory, and when the computer program is executed by the processor, implements the steps of the aforementioned method.

The technical solutions provided in the embodiments of the present application have at least the following technical effects or advantages:

The above description is only an overview of the technical solutions of the present invention, in order to be able to understand the technical means of the present invention more clearly, it can be implemented according to the content of the description, and in order to make the above and other purposes, features and advantages of the present invention more obvious and easy to understand , the following specific embodiments of the present invention are given.

Description of drawings

Various other advantages and benefits will become apparent to those of ordinary skill in the art upon reading the following detailed description of the preferred embodiments. The drawings are for the purpose of illustrating preferred embodiments only and are not to be considered limiting of the invention. Also, the same components are denoted by the same reference numerals throughout the drawings. In the attached image:

1 shows a flowchart of an evaluation method according to an embodiment of the present invention;

FIG. 2 shows a schematic diagram of the division of the non-intersection driving behavior coverage area;

Figure 3 shows a schematic diagram of the division of the driving behavior coverage area at the intersection.

Detailed ways

Exemplary embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. While exemplary embodiments of the present disclosure are shown in the drawings, it should be understood that the present disclosure may be embodied in various forms and should not be limited by the embodiments set forth herein. Rather, these embodiments are provided so that the present disclosure will be more thoroughly understood, and will fully convey the scope of the present disclosure to those skilled in the art.

The present invention conducts driving behavior safety assessment based on real-time detection data of handheld mobile terminals (including mobile phones), real-time signal light status data and road network data stored in the cloud. The present invention specifically provides a driving behavior safety assessment method, as shown in FIG. 1 , the method includes:

S1. Pre-stored road network data, the road network data includes road descriptive data and intersection signal descriptive data;

S2. Acquiring driving state data, the driving state data includes a driver ID, a driving time, a geographic location, a driving speed and a driving acceleration;

S3. Divide the driving state data into intersection data and non-intersection data according to the distance of the traveler from the intersection;

S4. Evaluate the non-intersection driving behavior according to the non-intersection data and the corresponding road network data;

S5. Evaluate the driving behavior at the intersection according to the intersection data, the corresponding road network data and the real-time obtained intersection signal light status data;

S6. Calculate the driving safety index according to the foregoing evaluation results.

The steps of the method can be implemented by a computer application program that can run on the server processor, and the computer program is stored in the memory of the server, or part of the steps can be implemented by running a client application program on the handheld mobile terminal processor or For all steps, the client application is stored in the memory of the mobile terminal.

In step S1, the road network data is structured data used to describe the connection relationship between roads and road latitude and longitude information. The data provides the specific latitude and longitude position of each intersection, road direction, road complexity and other information, which can be divided into Descriptive data for roads and descriptive data for intersection lights. The road descriptive data includes fields such as road ID, road latitude and longitude sequence, road traffic direction, road length, and road lane number; intersection signal light descriptive data includes signal light ID, signal light longitude and latitude, signal light phase, and road ID corresponding to the signal light phase pair, etc. field. Road network data is not real-time data and can be stored in advance.

其中

表示骑行人员i在时刻t^j所对应的形式状态数据向量，

分别表示该时刻行驶人员经纬度信息，

分别表示该时刻行驶人员速度及加速度信息。In step S2, real-time driving status data can be provided through a handheld mobile terminal (including a mobile phone), and specifically, it can be regularly uploaded through a mobile phone APP (a business-related APP used by practitioners). The existing APP can already upload the specific location of the cyclist, so that customers can know the specific location of the logistics. In the present invention, the mobile phone detects the location (longitude and latitude information), time, driving speed and acceleration of the driver to form the collected data, and the APP installed on the mobile phone collects the collected data and uploads it to the server. The driving state information can be expressed in vector form:

in

represents the formal state data vector corresponding to cyclist i at time t ^j ,

respectively represent the longitude and latitude information of the driver at the moment,

Respectively represent the speed and acceleration information of the traveler at this moment.

The matrix form of further available driving state data is as follows:

where n represents the number of sampling points. For some cases where the speed data is missing, it can be calculated and supplemented according to the latitude and longitude data. The calculation is as follows:

where length(*) represents the mapping formula for calculating the Euclidean distance based on the latitude and longitude between two points, and t _th is the judging threshold for the continuity of the latitude and longitude trajectory, that is, the time interval between the current and last two sampling points is less than the threshold, then the trajectory is considered to be continuous, Its value can be taken as 3min (may be determined according to the specific situation). Similarly, for the missing acceleration data, it can be calculated as follows:

The signal light status data is data indicating the real-time status of each signal light, and can be used to determine the traffic status of a specific phase at a specific intersection. The signal light status data can generally be obtained through the signal light related interface, and can also be obtained by calculation through Internet mobile data. Since the specific calculation method is not the focus of the present invention, it will not be described in detail here.

The present invention processes and analyzes the above-mentioned data to evaluate the safety of driving behavior. The present invention can collect data by using the intelligent mobile terminal that is widely carried by everyone, and does not require special installation on the vehicle. The device, which hardly costs any additional hardware costs, is easy to implement and promote.

As a specific implementation manner, the above real-time data needs to be preprocessed to ensure the reliability and validity of the data. First, abnormal data filtering and data division are performed on the driving state data.

的数据记录并滤除，其中v_th表示电动自行车可达到的最大速度(可根据实际情况进行设定)。Abnormal data filtering is to filter out the data that does not conform to the actual situation in the collected driving status data. Abnormal data is usually caused by abnormal detectors, data transmission errors, etc., and filtering out this part of the data is beneficial to ensure the reliability of the data. Sexuality and effectiveness of subsequent treatment. When the driving behavior safety assessment method is used for electric vehicle riding, the data detected by the mobile phone is included in the

The data is recorded and filtered, where v _th represents the maximum speed that the electric bicycle can reach (can be set according to the actual situation).

Data division refers to dividing the complete electric bicycle riding trajectory into the riding stage and the service provision stage, in which the riding stage refers to the stage where the cyclist rides the electric bicycle to complete the position movement, that is, the stage of normal riding behavior; service provision Stage, that is, the stage when the cyclist arrives at the location of the service demander and provides service for the demander. Since the position transfer has been completed in this stage, the mobile phone detection data does not correspond to the riding behavior of the electric bicycle. The present invention divides the complete mobile phone detection data based on the position and speed changes at the beginning and ending stages of riding, and only takes the behavior data at the riding stage as the object of subsequent research. You can set a certain time interval before and after the start and end time of riding, and take the riding behavior far from the starting and ending time as the behavior of the riding stage. Through data division, the effective driving state data can be separated.

The second step is to use the road network data to correct the geographic location information collected in real time. The obtained geographic location information is matched with the pre-stored road network data to obtain the matched road latitude and longitude mapping points as the processed geographic location of the traveler. Road matching refers to matching the latitude and longitude sampling points in the data collected by the mobile phone with their corresponding road IDs, and calculating the road latitude and longitude mapping points after matching. Because the mobile phone collected data has detection errors and longitude and latitude offsets to a certain extent, it is reliable and effective for road matching. The algorithm is beneficial to make a more accurate judgment on whether the electric bicycle is driving into the intersection, making the analysis result more reliable. The road matching work can be completed by the current relatively common road matching algorithm, or can be completed by calling the road matching service provided by the current Internet platform.

The present invention calculates the driving behavior index from multiple aspects based on the effective driving state data through steps S3, S4 and S5, so as to reflect the driving behavior more comprehensively.

Since the embodiment of driving safety depends not only on the driver's own driving habits, but also on the traffic environment where the driver is located, the present invention calculates the safety index from two aspects of non-intersection driving behavior and intersection driving behavior. Among them, the non-intersection driving behavior refers to the driving behavior of the driver in the process of driving on the normal road (not approaching the intersection), and the intersection driving behavior refers to the driving behavior of the driver in the process of passing through the intersection.

The following takes an electric bicycle as an example to illustrate.

According to the distance between the electric bicycle and the intersection, the non-intersection riding behavior and the intersection riding behavior are divided. As shown in Figure 2, the distance threshold Ld is preset, and the behavior when the distance between the electric bicycle and the nearest intersection is greater than Ld is divided. It is a non-intersection behavior, and the distance from the upstream and downstream of the intersection is Ld and the behavior within Ld is divided into intersection riding behavior.

If necessary, the coverage of non-intersection riding behavior and the coverage of intersection riding behavior can overlap to some extent, as shown in Figure 3. Pre-set the first distance threshold Ld and the second distance threshold Ld1, where Ld>Ld1; calculate the distance between the cyclist's geographic location and the nearest intersection; if the calculated distance is less than the threshold Ld, it will be The driving state data corresponding to the geographical location of the cyclist is divided into intersection data; if the calculated distance is greater than the threshold Ld1, the driving state data corresponding to the geographical location of the cyclist is divided into non-intersection data.

The non-intersection driving behavior is evaluated according to the non-intersection data and the corresponding road network data, which specifically includes: calculating the speed stability index according to the driving speed; calculating the speed abrupt change index according to the driving acceleration; according to the driving speed and the road description The performance data calculates the speed overspeed performance indicator.

The non-intersection riding behavior evaluation is based on the non-intersection riding data. Through the processing of this part of the riding data, the indicators are evaluated from the aspects of speed stability, rapid acceleration and deceleration behavior, and speeding behavior.

a) Evaluation of speed stability index

Riding stability refers to the ability of the cyclist to maintain the speed stability and the speed change process during the riding process. The speed stability reflects the driver's own sensitivity and adjustment ability to the driving speed, while the speed change process stability reflects Improve the driver's driving prediction ability and driving habits.

Assume that the non-intersection riding behavior speed change vector of cyclist i is as follows:

表示时刻tj检测到的骑行速度。则速度稳定性指标可定义如下：in

Indicates the riding speed detected at time tj. Then the speed stability index can be defined as follows:

进行处理的过程，本发明中可通过统计计算

向量的方差形式实现，即其含义为

其中N表示采样点个数，u表示所有采样点均值；D表示参照值，可根据实际情况进行设定；max(x,y)表示取x,y间较小的值。指标值α^a∈[0,1]，且取值越大，骑行安全性越好。Among them, g( ) represents the high-pass filtering process for time series, which can be realized by Gaussian filtering, wavelet filtering, etc.; f( ) represents the processed high-frequency velocity fluctuation data

The process of processing, in the present invention, can be calculated by statistical calculation

The variance form implementation of the vector, that is, its meaning is

Among them, N represents the number of sampling points, u represents the average value of all sampling points; D represents the reference value, which can be set according to the actual situation; max(x, y) represents the smaller value between x and y. The index value α ^a ∈ [0,1], and the larger the value, the better the riding safety.

b) Evaluation of rapid acceleration and deceleration behavior indicators

The rapid acceleration and deceleration behavior refers to the rapid acceleration and deceleration behavior of the cyclists during the riding process. It is caused by the cyclist's own driving behavior (sudden acceleration) or driving misjudgment (such as sudden deceleration caused by pedestrians not being detected in time). The rapid acceleration and deceleration of the cyclist is likely to cause a certain sudden impact on the subsequent drivers, which is a major traffic hazard, so it is an important indicator for evaluating riding safety.

It is assumed that the acceleration change vector of the non-intersection riding behavior of the cyclist i is as follows:

表示时刻tj检测到的加速度。则急加减速指标可定义如下：in

represents the acceleration detected at time tj. Then the rapid acceleration and deceleration index can be defined as follows:

表示是否属于急加减速度判断函数，其表达式如下：Among them, D ^b represents the reference value, which can be set according to the actual situation.

Indicates whether it belongs to the judgment function of rapid acceleration and deceleration, and its expression is as follows:

Among them, a _th is the acceleration and deceleration threshold, which can be set according to the actual situation.

The index value α ^b ∈ [0,1], and the larger the value, the better the riding safety.

c) Evaluation of speeding behavior indicators

Speeding behavior refers to the riding speed of the cyclist exceeding the driving limit (or other specified speed limit) of the driving road. Due to the poor stability of the electric bicycle itself, higher driving speed will bring greater safety risks, and the speeding behavior To a certain extent, it reflects the driving concepts and habits of the riders themselves, and is an important indicator for evaluating riding safety.

Assume that the non-intersection riding behavior speed change vector of cyclist i is as follows:

表示时刻t^j检测到的骑行速度。则超速行为指标可定义如下：in

represents the riding speed detected at time ^tj . Then the speeding behavior index can be defined as follows:

表示骑行人员超速行驶的总距离，h′(v)表示是否属于超速行驶的判断函数，其表达式如下：where Li represents the total length of ^cyclists riding in non-intersection behaviors,

Represents the total distance traveled by the cyclist over speeding, h′(v) represents the judgment function of whether it is speeding, and its expression is as follows:

Among them, v _th is the speed threshold, which can be set according to the actual situation.

The index value α ^c ∈ [0,1], and the larger the value, the better the riding safety.

Evaluate the driving behavior at the intersection according to the intersection data, the corresponding road network data and the real-time acquired intersection signal light status data, which specifically includes: according to the acquired matching vector and real-time matching vector of the geographic location of the traveler and the road network data The obtained intersection red light cycle judges whether there is a red light running behavior; according to the intersection driving acceleration and the intersection signal light status data obtained in real time, it is judged whether there is an intersection acceleration driving behavior; according to the obtained traffic location and road network data The matching vector and acceleration vector of , determine whether there is a sharp steering behavior. Finally, the above judgment results can be combined to calculate the intersection behavior index.

The intersection riding behavior evaluation is based on the intersection riding data, and through the processing of this part of the riding data, it is evaluated from the perspective of irregular behaviors such as red light running behavior, acceleration driving behavior, and sharp turning behavior.

a) Discrimination of the behavior of running a red light

The behavior of running a red light refers to the behavior of cyclists who do not obey the traffic light dispatch at the intersection and cross the intersection during the red light cycle. Since the intersection provides traffic services for vehicles in multiple directions at the same time, the driving behavior that does not obey the signal light scheduling is likely to conflict with the driving behavior of vehicles in other directions, resulting in the occurrence of traffic accidents. Therefore, the behavior of running a red light should be used as an indicator of safety assessment.

及结束时间为

其对应的交叉口骑行行为检测数据道路匹配向量为Based on the signal light status data, the specific time period of the red light cycle on the travel phase corresponding to the cyclist can be obtained. Taking intersection k as an example, it is assumed that the start time of the red light cycle corresponding to the riding behavior at the intersection is

and the end time is

The corresponding road matching vector of the intersection riding behavior detection data is:

表示骑行人员i在t^j时刻所在道路的道路ID，假设信号灯相位上游影响路段集合为R^u，下游集合为R^d，则可定义闯红灯判断函数如下：in

Represents the road ID of the road where the cyclist i is located at time t ^j . Assuming that the upstream set of road segments affected by the signal light phase is R ^u and the downstream set is R ^d , the red light running judgment function can be defined as follows:

That is, when it is detected that the cyclist has crossed the intersection during the red light cycle, it is judged that he has run the red light, that is,

b) Judgment of the behavior of accelerating and entering the intersection

及结束时间为

其对应的交叉口骑行行为加速度向量为The behavior of accelerating into the intersection means that the cyclist does not take deceleration measures at the intersection, but instead accelerates into the intersection, which usually occurs when the cyclist rushes through the intersection before the red light. Due to the complex traffic environment at the intersection, the stability of the electric bicycle is poor, and there is a certain safety risk in the fast acceleration driving behavior. Taking intersection k as an example, it is assumed that the start time of the green light cycle corresponding to the riding behavior at the intersection is

and the end time is

The corresponding acceleration vector of the riding behavior at the intersection is

表示骑行人员i在t^j时刻的加速度值，在检测到骑行人员穿过交叉口的基础上，则可定义加速驶入行为判断函数如下：in

represents the acceleration value of cyclist i at time t ^j . On the basis of detecting the cyclist passing through the intersection, the judgment function of acceleration and entering behavior can be defined as follows:

That is, when it is detected that the cyclist accelerates through the intersection before the end of the green light, it is judged that there is an acceleration to enter, that is,

c) Judgment of sharp turning behavior

Steering behavior at intersections means that cyclists do not decelerate significantly during the process of turning at intersections, but maintain a relatively high speed for steering operations. Due to the poor stability of electric bicycles, there is a certain safety risk in the faster steering behavior.

及结束时间为

其对应的交叉口骑行行为道路匹配向量及加速度向量为Taking intersection k as an example, it is assumed that the start time of the green light cycle corresponding to the riding behavior at the intersection is

and the end time is

The corresponding intersection riding behavior, road matching vector and acceleration vector are

表示骑行人员i在t^j时刻所在道路的道路ID，

表示骑行人员i在t^j时刻速度，假设信号灯相位上游影响路段集合为R^u，下游转向集合为R^d，同时统计得在绿灯周期内骑行平均速度为

则急转向行为判断函数如下in

is the road ID of the road where cyclist i is located at time t ^j ,

Represents the speed of cyclist i at time t ^j , assuming that the set of upstream affected sections of the signal light phase is R ^u , and the set of downstream steering sets is R ^d , and the average speed of riding in the green light period is calculated as

Then the sharp steering behavior judgment function is as follows

That is, when it is detected that the cyclist is turning at a higher speed during the green light period, it is determined that there is a sharp turning behavior, that is,

d) Evaluation of intersection behavior indicators

Based on the above discriminant function, it can be further determined that after the cyclists pass through multiple intersections, the intersection behavior evaluation index can be defined as follows:

Among them, K represents the number of intersections passed in the evaluation time period.

The index value β∈[0,1], and the larger the value, the better the riding safety.

The calculation of the driving safety index according to the foregoing evaluation results specifically includes: for a single driving process, weighted calculation of the driving safety index according to the above indicators; for multiple driving processes, weighted calculation of the single driving safety index according to the travel period to obtain the total driving safety level.

To evaluate the safety reflected in the single delivery process of cyclists and the multiple delivery processes of cyclists, the following implementation methods can be adopted:

(1) Single riding process

In the single delivery process, the time span of the riding data is short, and the index values α ^a α ^b α ^c and β can be calculated by using the mobile phone detection data, and then in the form of weighted summation, the single riding safety index of the cyclists can be calculated. is evaluated with the following expression:

where x ₁ , x ₂ , x ₃ , x ₄ represent the weight coefficients

(2) Multiple rides

晚间时段骑行安全指数

其他时段骑行安全指数

最终可得综合安全评估指数如下：The multiple riding process covers the riding records in different time periods and reflects the riding habits of the cyclists in different time periods. Divide the riding period into three periods: peak period (such as 7:00-9:00, 17:00-20:00), evening period (such as 20:00-06:00), and other periods. Calculate the corresponding safety index values α ^a α ^b α ^c and β within the time period, and obtain the riding safety index during peak hours by weighting

Cycling safety index at night

Cycling safety index at other times

The final comprehensive safety assessment index is as follows:

Through the calculation of the index, it can directly reflect the driver's safety and directly reflect the driver's driving safety degree on the basis of synthesizing all aspects of driving behavior.

The above-mentioned embodiments of the present invention are mainly described by taking an electric bicycle as an example. In fact, the present invention is not only applicable to electric bicycles, but also applicable to other means of transportation such as automobiles (including passenger cars and trucks), and is applicable to all kinds of vehicles that need to evaluate the driving behavior of drivers. The security scenario is especially suitable for the situation where the service industry drives the vehicle for multiple service personnel and the vehicle is shared.

The invention proposes a rider's safe riding index system, which evaluates the rider's riding safety factor from different aspects, provides data support for the optimized management of riders, and is beneficial to improving the service level of short-distance distribution business.

The technical solutions provided in the embodiments of the present application have at least the following technical effects or advantages:

It can evaluate the safety of driving behavior of drivers, so as to provide data support and basis for the optimal management of drivers (riding), which is conducive to improving the service level of the distribution service industry.

The algorithms and processes, analyses provided herein are not inherently related to any particular computer, virtual system, or other device. Various general-purpose systems can also be used with teaching based on this. The structure required to construct such a system is apparent from the above description. Furthermore, the present invention is not directed to any particular programming language. It is to be understood that various programming languages may be used to implement the inventions described herein, and that the descriptions of specific languages above are intended to disclose the best mode for carrying out the invention.

In the description provided herein, numerous specific details are set forth. It will be understood, however, that embodiments of the invention may be practiced without these specific details. In some instances, well-known methods, structures and techniques have not been shown in detail in order not to obscure an understanding of this description.

Similarly, it is to be understood that in the above description of exemplary embodiments of the invention, various features of the invention are sometimes grouped together into a single embodiment, figure, or its description. This disclosure, however, should not be construed as reflecting an intention that the invention as claimed requires more features than are expressly recited in each claim. Rather, as the following claims reflect, inventive aspects lie in less than all features of a single foregoing disclosed embodiment. Thus, the claims following the Detailed Description are hereby expressly incorporated into this Detailed Description, with each claim standing on its own as a separate embodiment of this invention.

It should be noted that the above-described embodiments illustrate rather than limit the invention, and that alternative embodiments may be devised by those skilled in the art without departing from the scope of the appended claims. In the claims, any reference signs placed between parentheses shall not be construed as limiting the claim. The word "comprising" does not exclude the presence of elements or steps not listed in a claim. The word "a" or "an" preceding an element does not exclude the presence of a plurality of such elements. The invention can be implemented by means of hardware comprising several different elements and by means of a suitably programmed computer.

Claims (12)

1. A driving behavior safety assessment method, running a client application program on a hand-held mobile terminal processor to realize part of the steps or all of the steps, it is characterized in that, the method comprises: Pre-stored road network data, the road network data includes road descriptive data and intersection signal descriptive data; Acquiring driving status data through the intelligent mobile terminal, the driving status data including the driver ID, driving time, geographic location, driving speed and driving acceleration; Divide the driving state data into intersection data and non-intersection data according to the distance of the traveler from the nearest intersection; The speed stability index is calculated according to the driving speed information in the non-intersection data, the speed sharpness index is calculated according to the driving acceleration in the non-intersection data, and the speed and road descriptiveness are calculated according to the driving speed and road descriptiveness in the non-intersection data. Data calculation speed overspeed index; According to the matching vector of the geographic location of the driver obtained from the intersection data and the road network data and the real-time intersection red light cycle to determine whether there is a red light running behavior, according to the driving acceleration in the intersection data and the real-time obtained intersection signal status According to the matching vector and acceleration vector of the geographic location of the driver in the obtained intersection data and the road network data, it is judged whether there is a sharp turning behavior; The driving safety index is calculated according to each index and each behavior judgment result. 2. The method according to claim 1, wherein the method further comprises: The obtained geographic location information is matched with the pre-stored road network data to obtain the matched road latitude and longitude mapping points as the processed geographic location of the traveler. 3. The method according to claim 1 or 2, wherein the driving state data is divided into intersection data and non-intersection data according to the distance of the traveler from the intersection, specifically comprising: Preset the first distance threshold Ld before the intersection, and the second distance threshold Lb after the intersection; Calculate the distance between the geographic location of the traveler and the nearest intersection; If the distance calculated before passing through the intersection is less than the threshold value Ld, or the distance calculated after passing through the intersection is less than the threshold value Lb, the driving state data corresponding to the geographic location of the traveler is divided into intersection data, Otherwise, it is classified as non-intersection data. 4. The method according to claim 1 or 2, wherein the driving state data is divided into intersection data and non-intersection data according to the distance of the traveler from the nearest intersection, specifically including: Preset the first distance threshold Ld before the intersection and the second distance threshold Ld1 before the intersection, where Ld>Ld1; Calculate the distance between the geographic location of the pedestrian before the intersection and the nearest intersection; If the calculated distance is less than the threshold Ld, the driving state data corresponding to the geographic location of the traveler is divided into intersection data; If the calculated distance is greater than the threshold value Ld1, the traveling state data corresponding to the geographic location of the traveler is classified as non-intersection data. 5. The method of claim 1, further comprising: The intersection behavior index is calculated according to the judgment result. 6. method according to claim 1 is characterized in that, step: calculate driving safety index according to each index and each behavior judgment result, specifically comprises: For a single driving process, the driving safety index is weighted according to each index and behavior judgment result. 7. The method according to claim 1, wherein the driving safety index is calculated according to each index and each behavior judgment result, specifically comprising: For the multiple driving process, the single driving safety index is weighted according to the travel period to obtain the total driving safety index. 8. The method according to claim 1, further characterized in that, in the step of: acquiring driving state data, the method further comprises: extracting valid driving state data from the acquired driving state data, specifically including filtering abnormal data And/or extract data greater than a predetermined travel speed. 9. The method according to claim 1, which is used for evaluating the riding behavior of an electric vehicle. 10. A storage medium for storing a computer program, wherein the computer program is used to execute the method of any one of claims 1-9. 11. A server, characterized in that the server comprises a memory, a processor and a computer program stored on the memory, the computer program implementing the method according to any one of claims 1-9 when the computer program is executed by the processor step. 12. A hand-held terminal, characterized in that the terminal comprises a memory, a processor and a computer program stored on the memory, the computer program being executed by the processor to implement the method according to any one of claims 1-9 A step of.

Images