CN116001800A

CN116001800A - Vehicle driving risk information acquisition method and device, electronic equipment and medium

Info

Publication number: CN116001800A
Application number: CN202211720605.9A
Authority: CN
Inventors: 杨策; 刘浩; 凌盛; 李忠; 朱子凡
Original assignee: China Unicom Smart Connection Technology Ltd; Unicom Intelligent Network Ruixing Technology Beijing Co Ltd
Current assignee: China Unicom Smart Connection Technology Ltd; Unicom Intelligent Network Ruixing Technology Beijing Co Ltd
Priority date: 2022-12-30
Filing date: 2022-12-30
Publication date: 2023-04-25
Anticipated expiration: 2042-12-30
Also published as: CN116001800B

Abstract

The embodiment of the application provides a method, a device, electronic equipment and a medium for acquiring vehicle driving risk information, wherein the method comprises the following steps: for each first event related to the first driving risk, monitoring whether the target vehicle has the first event, if so, acquiring information of each first parameter of the target vehicle, wherein the first parameter is a driving related parameter which is related to the first event and affects the risk degree of the first event; determining risk degree indication information of a first event of the target vehicle according to the information of each first parameter of the target vehicle; and obtaining risk degree indicating information of the first driving risk of the target vehicle according to the risk degree indicating information of each first event of the target vehicle. According to the method and the device for determining the driving risk of the vehicle, the driving risk of the vehicle can be accurately determined, and the driving safety of the vehicle can be guaranteed.

Description

Vehicle driving risk information acquisition method and device, electronic equipment and medium

Technical Field

The present disclosure relates to the field of vehicle technologies, and in particular, to a method and apparatus for acquiring driving risk information of a vehicle, an electronic device, and a medium.

Background

In order to ensure the driving safety of the vehicle, the driving risk of the vehicle can be determined according to the driving data of the vehicle.

In one possible implementation, the duration of continuous ignition of the vehicle may be collected by an ignition monitoring device and the risk of driving the vehicle determined therefrom.

But the accuracy of the vehicle driving risk obtained by the existing implementation is poor. For example, during large traffic jams, the vehicle is usually idling for a long time without flameout, the long-term ignition behavior is substantially quite limited to the real hazard of safe driving, and the accuracy of the ignition monitoring recognition result is easily affected by equipment hardware aging.

Disclosure of Invention

The embodiment of the application provides a vehicle driving risk information acquisition method, device, electronic equipment and medium, which can accurately determine the vehicle driving risk and are beneficial to guaranteeing the vehicle driving safety.

In a first aspect, an embodiment of the present application provides a method for acquiring driving risk information of a vehicle, including: for each first event related to a first driving risk, monitoring whether the first event exists in the target vehicle; acquiring information of each first parameter of the target vehicle under the condition that the first event exists in the target vehicle, wherein the first parameter is a driving related parameter associated with the first event and affects the risk degree of the first event; determining risk degree indication information of the first event of the target vehicle according to information of each first parameter of the target vehicle; and obtaining risk degree indicating information of the first driving risk of the target vehicle according to the risk degree indicating information of each first event of the target vehicle.

Optionally, the risk level indication information of the first event of the target vehicle includes: a risk score for the first event of the target vehicle; the obtaining risk degree indicating information of the first driving risk of the target vehicle according to the risk degree indicating information of each first event of the target vehicle includes: determining a score range in which a first score falls according to a plurality of preset score ranges corresponding to the first driving risk, wherein the score ranges correspond to a plurality of risk grades one by one, and the first score is obtained according to the risk score of each first event of the target vehicle; and taking the risk level corresponding to the score range in which the first score falls as risk level indication information of the first driving risk of the target vehicle.

Optionally, the risk level indication information of the first event of the target vehicle includes: a risk score for the first event of the target vehicle; the determining risk level indication information of the first event of the target vehicle includes: acquiring a preset score of the first event and a preset score of information of the first parameter of the target vehicle aiming at the first event; taking the product of the obtained preset scores as a risk score of the first event of the target vehicle.

Optionally, in the case that the first driving risk is a aggressive driving risk, the first event related to the first driving risk includes: at least one of lane change event, front vehicle approaching event and overspeed event; the event that the front vehicle is close indicates that the distance between the vehicle and the front vehicle is smaller than a preset distance threshold value; the respective driving related parameters associated with the lane change event involved in the aggressive driving risk include: at least one of vehicle speed, driving scene, number of continuous lane change, road gradient, and duration; the respective driving related parameters associated with the preceding vehicle approaching event related to the aggressive driving risk include: at least one of distance from the front vehicle, vehicle speed, driving scene, number of times of continuous front vehicle, road gradient of driving and continuous driving duration; the individual driving related parameters associated with the overspeed event related to the aggressive driving risk include: at least one of vehicle speed, driving scene, number of continuous overspeed, road gradient, and duration.

Optionally, the acquiring information of each first parameter of the target vehicle includes: in the case where the driving-related parameter associated with the first event includes a running road surface gradient, according to two positioning positions and two altitudes of the target vehicle at two points in time, wherein the positioning positions include longitude and latitude, the two points in time being a start time point and an end time point at which the first event exists in the target vehicle; acquiring the distance between the two positioning positions; acquiring a height difference value between the two altitudes; and obtaining a gradient value of the gradient of the running road surface of the target vehicle associated with the first event according to the distance between the two positioning positions and the height difference between the two altitudes.

Optionally, in the case that the first driving risk is a fatigue driving risk, the first event related to the first driving risk includes: at least one of an eye closure event, a yawning event, a vehicle continuous ignition event; the respective driving related parameters associated with the eye-closure event related to the fatigue driving risk include: at least one of vehicle speed, number of continuous eye closure, road congestion, and duration of driving; the respective driving related parameters associated with the yawing event related to the fatigue driving risk include: at least one of vehicle speed, number of continuous yawing, road congestion condition and continuous driving duration; the respective driving related parameters associated with the vehicle consecutive ignition event related to the fatigue driving risk include: at least one of vehicle speed, road congestion condition, duration of driving.

Optionally, the risk level indication information of the first event of the target vehicle includes: a risk score for the first event of the target vehicle; the obtaining risk degree indicating information of the first driving risk of the target vehicle according to the risk degree indicating information of each first event of the target vehicle includes: comparing a second score with a preset score threshold under the condition that the first driving risk is fatigue driving risk, wherein the second score is obtained according to the risk score of each first event of the target vehicle, and the risk score is positively related to the risk degree; acquiring first information when the second score is greater than the score threshold value, wherein the first information is used for indicating that the target vehicle has at least one of the information of the alarm event of the approaching front vehicle alarm, the collision alarm of the front vehicle and the approaching pedestrian alarm in the associated time period of the first event of the target vehicle; and obtaining risk degree indicating information of the first driving risk of the target vehicle according to the first information and the second score.

In a second aspect, an embodiment of the present application provides a vehicle driving risk information acquisition device, including: a monitoring module for monitoring, for each first event related to a first driving risk, whether the first event exists in the target vehicle; a first obtaining module, configured to obtain information of each first parameter of the target vehicle when the first event exists in the target vehicle, where the first parameter is a driving related parameter associated with the first event, and the first parameter affects a risk degree of the first event; a determining module, configured to determine risk level indication information of the first event of the target vehicle according to information of each first parameter of the target vehicle; the second acquisition module is used for acquiring risk degree indicating information of the first driving risk of the target vehicle according to the risk degree indicating information of each first event of the target vehicle.

In a third aspect, an embodiment of the present application provides an electronic chip, including: a processor for executing computer program instructions stored on a memory, wherein the computer program instructions, when executed by the processor, trigger the electronic chip to perform the method according to any of the first aspects.

In a fourth aspect, embodiments of the present application provide an electronic device comprising a memory for storing computer program instructions, a processor for executing the computer program instructions, and communication means, wherein the computer program instructions, when executed by the processor, trigger the electronic device to perform a method as in any of the first aspects.

In a fifth aspect, embodiments of the present application provide a computer-readable storage medium having a computer program stored therein, which when run on a computer, causes the computer to perform the method as in any of the first aspects.

In a sixth aspect, embodiments of the present application provide a computer program product comprising a computer program which, when run on a computer, causes the computer to perform the method as in any of the first aspects.

In the embodiment of the application, for each first event related to the first driving risk, whether the target vehicle has the first event is monitored, if so, information of each first parameter of the target vehicle is obtained, and the first parameter is a driving related parameter which is related to the first event and affects the risk degree of the first event; determining risk degree indication information of a first event of the target vehicle according to the information of each first parameter of the target vehicle; and obtaining risk degree indicating information of the first driving risk of the target vehicle according to the risk degree indicating information of each first event of the target vehicle. It can be seen that, unlike the implementation manner in the prior art that the driving risk of the vehicle is determined only according to the driving risk event (such as the continuous ignition duration of the vehicle, etc.), when the driving risk event occurs to the vehicle, the embodiment of the application combines the driving related information which is associated with the driving risk event and can affect the risk degree thereof to determine the substantial risk degree of the driving risk event of the vehicle, thereby determining the driving risk of the vehicle according to the substantial risk degree, so that the driving risk of the vehicle can be accurately determined, and the driving safety of the vehicle is facilitated to be ensured.

Drawings

In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings that are needed in the embodiments will be briefly described below, and it is obvious that the drawings in the following description are only some embodiments of the present application, and that other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.

Fig. 1 is a schematic flow chart of a method for acquiring driving risk information of a vehicle according to an embodiment of the present application;

fig. 2 to 6 are schematic diagrams of five driving situations of a vehicle according to one embodiment of the present application;

FIG. 7 is a schematic diagram of a method for determining grade value according to one embodiment of the present application;

FIG. 8 is a block schematic diagram of a vehicle driving risk information acquisition device according to an embodiment of the present application;

fig. 9 is a schematic structural diagram of a computer device according to an embodiment of the present application.

Detailed Description

For a better understanding of the technical solutions of the present application, embodiments of the present application are described in detail below with reference to the accompanying drawings.

It should be understood that the described embodiments are merely some, but not all, of the embodiments of the present application. All other embodiments, based on the embodiments herein, which would be apparent to one of ordinary skill in the art without making any inventive effort, are intended to be within the scope of the present application.

The terminology used in the embodiments of the application is for the purpose of describing particular embodiments only and is not intended to be limiting of the application. As used in this application and the appended claims, the singular forms "a," "an," and "the" are intended to include the plural forms as well, unless the context clearly indicates otherwise.

It should be understood that the term "at least one" as used herein means one or more, and "a plurality" means two or more. The term "and/or" as used herein is merely one association relationship describing the associated object, meaning that there may be three relationships, e.g., a and/or B, may represent: a exists alone, A and B exist together, and B exists alone. Wherein A, B may be singular or plural. In addition, the character "/" herein generally indicates that the front and rear associated objects are an "or" relationship. "at least one of the following" and the like means any combination of these items, including any combination of single or plural items. For example, at least one of a, b and c may represent: a, b, c, a-b, a-c, b-c, or a-b-c, wherein a, b, c may be single or plural.

It should be understood that although the terms first, second, etc. may be used in embodiments of the present application to describe the set threshold values, these set threshold values should not be limited to these terms. These terms are only used to distinguish the set thresholds from each other. For example, a first set threshold may also be referred to as a second set threshold, and similarly, a second set threshold may also be referred to as a first set threshold, without departing from the scope of embodiments of the present application.

The terminology used in the description section of the present application is for the purpose of describing particular embodiments of the present application only and is not intended to be limiting of the present application.

In order to ensure the driving safety of the vehicle, the driving risk of the vehicle can be determined according to the driving data of the vehicle. When the vehicle has driving risk, corresponding reminding and control operations can be performed so as to avoid dangerous driving of the vehicle.

In one implementation (denoted implementation 1), the risk of driving the vehicle may be determined by measuring the speed by a roadside radar.

And the speed measuring radar can be erected on the roadside, the speed of the vehicle is measured through the speed measuring radar, whether the vehicle is overspeed or not and the overspeed degree are judged, and the driving risk of the vehicle is determined according to the overspeed result. For example, whether there is a risk of aggressive driving of the vehicle may be determined based on the overspeed result.

In another implementation (noted as implementation 2), the vehicle continuous ignition duration may be collected by an ignition monitoring device and the vehicle driving risk determined therefrom. For example, whether the driver is at risk of fatigue driving can be determined according to the continuous ignition duration of the vehicle.

In still another implementation manner (recorded as implementation manner 3), a camera with AI (Artificial Intelligence ) recognition capability may be installed at a driving position of a vehicle, and the installed camera is used to observe a situation of the front of the vehicle and behavior of a driver in the vehicle, so that AI learning and recognition may be performed for behaviors such as eye closure, ignition, smoke and the like when the driver drives the vehicle, and for behaviors such as approaching the front vehicle and lane change and the like in a solid line during driving of the vehicle, so as to recognize dangerous driving behaviors. Based on the identification of dangerous driving behavior, it can be determined whether there is a risk of aggressive driving of the vehicle, driver fatigue driving. And a corresponding safe driving alarm can be given according to the recognized dangerous driving behavior.

However, these implementations have the problem of single recognition scenario (problem 1 described below) and being easily interfered by other factors (problem 2 described below), which results in poor accuracy of the obtained risk of driving the vehicle, and often cannot accurately evaluate the risk of driving the vehicle. In addition, these implementations have a problem of inconvenience in management needs of enterprises (problem 3 described below), and inconvenience in on-demand flexible management of vehicle driving risks.

Problem 1: identifying a scene singleness

In the embodiment 1, only the vehicle speed of the vehicle can be recognized by the roadside radar test. Whether there is a risk of aggressive driving of the vehicle is determined from the vehicle speed.

In the embodiment 2, only the continuous ignition duration of the vehicle can be recognized by the ignition monitoring apparatus. And determining whether the fatigue driving risk of the driver exists according to the continuous ignition duration.

In the embodiment 3, the camera with AI recognition capability recognizes the features of the driver, such as the facial features of the driver, the approaching vehicle, and the lane change of the host vehicle. Whether the driver is at risk of fatigue driving is determined according to the facial features of the driver, and whether the vehicle is at risk of aggressive driving is determined according to the too close of the front vehicle and lane change of the vehicle.

However, driving safety risk identification is actually a comprehensive embodiment in a complex scene, and it is difficult to accurately evaluate the driving risk of the vehicle by using a single factor (such as a vehicle speed, a continuous ignition duration, a facial feature of a driver, and the like).

For example, during a large vehicle jam, the vehicle may idle for a long period without flameout or may be traveling at a slow speed, and the driver may experience facial movements such as eye-closing, yawning, etc. However, at zero or low vehicle speeds (e.g., near zero), the driver's facial motion, long-term ignition behavior, is substantially quite limited to the real hazard of safe driving.

For another example, although the roadside radar test can measure overspeed of the vehicle, road congestion, driver sight line, bad weather, etc. cannot be comprehensively considered.

In vehicle driving risk identification based on single factors, the behavior with real driving risk is easy to miss, a large number of risk alarms with small actual dangerous situations are also reported, so that a large amount of management manpower and financial resources are wasted, the management of drivers lacks pertinence, management fatigue is easy to achieve, and timeliness of commercial vehicles in transportation is particularly affected.

Problem 2: is easily interfered by other factors

The devices on which the implementation modes 1-3 depend are single (the information acquisition sources are single), and if the devices themselves fail, the corresponding identification effects can be greatly affected and even cannot be identified.

In the implementation mode 1, when the roadside radar monitors the vehicle speed under the condition of continuous running with a relatively close distance between multiple vehicles, the vehicles can be shielded from each other, so that each vehicle cannot be prevented from being monitored, and the roadside radar is easy to interfere with a plurality of vehicle-mounted radars of the vehicle.

In implementation 2, the accuracy of the ignition monitor recognition result is susceptible to degradation of the device hardware. Taking an ignition monitoring device as an on-board sensor of a vehicle as an example, the on-board sensor can judge whether the vehicle ignites or not through voltage variation, but the voltage is also influenced by voltage fluctuation caused when the vehicle turns on a high-power electric device.

In the implementation mode 3, the success rate of video AI learning is generally not 100% accurate in the current industry, and the camera is affected by factors such as humidity and brightness, so that the learning effect after imaging can be affected. In addition, the camera is easily deliberately shielded by a driver, so that the supervision effect cannot be achieved. Because the camera is installed in the car, if means such as manual shielding of the camera exist to block the collection, the problem that the collection cannot be effectively solved by remote means can only be solved by education and management standard aiming at related personnel, so that the initiative of monitoring means is insufficient.

Problem 3: inconvenient to be different according to the management requirement of enterprises

The management requirements of different enterprises in different time periods and different scenes can be different, and the dependent technical means can be different, but the implementation modes 1-3 are usually universal management modes, so that the management requirements of the enterprises are not convenient to flexibly customize according to the requirements.

As shown in fig. 1, an embodiment of the present application provides a method for acquiring driving risk information of a vehicle, including steps 101 to 104.

In one embodiment, the execution subject of the embodiment shown in fig. 1 may be an electronic device, which may be the vehicle itself, a server that maintains communication with the vehicle, or the like.

In one embodiment, by acquiring the information of the driving risk of the vehicle, it is not only possible to know whether the vehicle has a corresponding driving risk, but also know the degree of risk that the vehicle has a corresponding driving risk.

Step 101, for each first event related to the first driving risk, monitoring whether the target vehicle has a first event. Upon detecting that the target vehicle has a first event, step 102 may be performed. In one embodiment, if the first event is not detected in the target vehicle, the current flow may be ended.

In one embodiment, the target vehicle may be any vehicle that is monitorable, such as a two-passenger, heavy freight jeopardized vehicle.

When a driver drives the vehicle in an aggressive manner and drives the vehicle in a tired manner, the driving risk of the vehicle can be in an aggressive manner and a tired manner in a feasible implementation manner. The first driving risk may be either of these two driving risks.

In an embodiment, the two driving risks may be a first driving risk and a second driving risk, and based on the same implementation logic as the information for acquiring the first driving risk, the information for acquiring the second driving risk may also be acquired, and the corresponding specific implementation process may refer to the related technical description for the first driving risk.

In one embodiment, the first driving risk may relate to only one driving risk event (i.e. the first event described above), and in this embodiment, to learn whether the vehicle has the first driving risk, only whether the vehicle has occurred or is in existence of the driving risk event may be monitored.

In another embodiment, the first driving risk may involve more than one driving risk event, and in this embodiment, to learn whether the vehicle has a first driving risk, whether the vehicle has occurred or each driving risk event may be monitored separately.

Possibly, the driving risk event to be monitored may be an eye-closure event, a yawning event, a continuous ignition event of the vehicle, a lane change event, a near-front event, an overspeed event, etc.

In one embodiment, some driving related information of the vehicle, such as vehicle position, vehicle speed, distance from the preceding vehicle, facial features of the driver, etc., may be collected in real time, and whether the first event is present may be monitored based on the information collected in real time.

In one embodiment of the present application, the collected vehicle driving related information may be classified into information of parameters such as a vehicle itself data parameter, a driver related parameter, a vehicle front condition related parameter, a vehicle external environment parameter, and the like. The score may be flexibly assigned to different types of parameters.

In one embodiment, the vehicle-itself data parameters may include vehicle type, vehicle actual load, vehicle real-time speed, vehicle continuous ignition duration, vehicle latitude and longitude position, vehicle angle, vehicle altitude, tire pressure, etc.

In one possible implementation, the information of the data parameters of the vehicle itself can be obtained by the landmark vehicle-mounted device. The standard can meet the technical standards of forced supervision equipment, systems and data transmission of vehicles such as heavy freight and the like endangered by two passengers issued by the traffic department, and can realize acquisition and transmission of basic data of the vehicles such as positioning, vehicle speed, direction and the like. The standard may be simply referred to as a heading since it is issued by the traffic department.

In one embodiment, the driver-related parameters may include driver fatigue driving behavior (e.g., eye closure, yawning, etc.), driver distraction driving behavior (e.g., smoke, cell phone viewing, etc.), and the like.

In one possible implementation, the information of the driver related parameters may be obtained by an AI camera. The local standard can refer to local standards of equipment, systems and data transmission of vehicle supervision of various provinces on the basis of the local standard, and can be generally applied to the supervision and execution of two-passenger one-jeopardized heavy goods vehicles in the release province. The standard is issued by local province level and can be called local standard for short.

In one embodiment, the vehicle front condition related parameters may include a front vehicle approaching behavior, a lane change behavior, a vehicle front congestion condition, etc.

In one possible implementation, the information about the parameters related to the vehicle front condition can be obtained by an AI camera of the local standard video.

In one embodiment, the vehicle external environment parameters may include time, weather, road conditions, etc.

In one possible implementation, information about parameters of the environment outside the vehicle may be obtained through an external interface of a third party, such as traffic, weather department, etc.

In one possible implementation, the collection of the multidimensional sensory data may be implemented based on a road side device (e.g., traffic lights, etc.), an on-board device (e.g., on-board radar, a vehicle-road cooperative risk alarm, etc.), and more sensors.

In one embodiment of the present application, in a case where the first driving risk is a fatigue driving risk, the first event related to the first driving risk may include: at least one of an eye-closure event, a yawning event, a vehicle continuous ignition event.

In one embodiment of the present application, in a case where the first driving risk is a aggressive driving risk, the first event related to the first driving risk may include: at least one of lane change event, front vehicle approaching event and overspeed event; the event that the front vehicle is close indicates that the distance between the vehicle and the front vehicle is smaller than a preset distance threshold value.

In one embodiment, the lane change event related to the aggressive driving risk may be a lane change event in a highway driving scene (such as a highway lane change event).

In another embodiment, the driving risk event involved in the aggressive driving risk may be a lane change and front car approach event in a highway driving scenario. In one possible implementation manner, according to the real-time speed of the vehicle, and in combination with event information such as the lane change of the vehicle, whether the distance between the vehicle and the front vehicle is relatively close after the lane change, and the road attribute of the vehicle, whether the vehicle is in a driving risk event of high-speed lane change on an expressway and the distance between the vehicle and the front vehicle is relatively close after the lane change is judged.

Fig. 2-6 show five possible scenarios of lane change events in a highway driving scenario:

case 1: high speed lane change (i.e. lane change in a highway driving scene), high speed (i.e. higher speed, such as 90 km/h), non-continuous lane change, non-near front vehicle after high lane change, non-continuous driving (such as non-continuous driving for more than 5 h), non-downhill road section;

case 2: the method comprises the following steps of high-speed lane changing, high-speed continuous lane changing, no front vehicle is close after the high-speed lane changing, no continuous driving and no downhill road section;

Case 3: the method comprises the following steps of high-speed lane changing, high-speed continuous lane changing, and no continuous driving and no downhill road section when a front vehicle is close after the high-speed lane changing;

case 4: the method comprises the following steps of high-speed lane changing, high-speed continuous lane changing, and continuous driving of a front vehicle which is relatively close to a road section without a downhill road after the high-speed lane changing;

case 5: the high-speed lane change, the high-speed continuous lane change and the high-speed lane change are followed by the closer front vehicles and the downhill road sections.

In the five cases, although the vehicle also has a high-speed lane change event, the aggressive driving risk levels in the five cases may be different according to the difference of the associated information, and the aggressive driving risk levels in the case 1 to the case 5 may be substantially no risk in the aggressive driving LV1, a lower risk in the aggressive driving LV2, a low risk in the aggressive driving LV3, a risk in the aggressive driving LV4, and a high risk in the aggressive driving LV5, respectively.

When a preset driving risk event (such as lane change of a vehicle, eye closure of a driver and the like) occurs to the vehicle, the risk degree of the driving risk event can be available or not and can be large or small based on different conditions of the related parameters of the event, so that in order to accurately evaluate the driving risk, when the driving risk event occurs to the vehicle, the information of the related parameters of the driving risk event can be acquired, so that the risk degree of the driving risk event can be accurately evaluated by combining the information of the related parameters of the driving risk event, and the evaluated risk information can be kept in high consistency with the essence.

For example, when the driver of the vehicle is monitored to be closed, if the vehicle is in a congested driving scene, no driving risk can be considered. For another example, if the vehicle driver is monitored to be closed, the driving risk may be considered to be low if the vehicle driving speed is low and the number of times the driver continues to repeatedly close the eyes is small. For example, if the driver of the vehicle is detected to be in close eyes, and the vehicle is traveling on a highway at a high speed, the driver may consider that the driving risk is high if the driver continues to repeatedly close eyes more times.

In one embodiment, some driving related information of the vehicle, such as vehicle position, vehicle speed, distance from the preceding vehicle, facial features of the driver, etc., may be collected in real time, and whether the first event is present may be monitored based on the information collected in real time. In addition to monitoring whether the first event occurs or not, information of driving related parameters of the target vehicle associated with the first event, such as congestion conditions, weather information, up-down gradient, etc., may be obtained based on the information collected in real time.

And 102, under the condition that the first event exists in the target vehicle, acquiring information of each first parameter of the target vehicle, wherein the first parameter is a driving related parameter associated with the first event, and the first parameter influences the risk degree of the first event.

The influence of different information of the first parameter on the degree of risk of the first event may be different. For example, the longer the duration of the vehicle driver, the higher the risk of an eye closure event, and vice versa.

In one embodiment, the number of driving related parameters associated with the first event may be only one, and in this embodiment, only the information of the driving related parameters may be acquired, and then the risk level indication information of the first event of the target vehicle may be determined according to the information of the driving related parameters. Taking the driving related parameter as an example of the vehicle speed, the obtained corresponding information may be a specific vehicle speed value.

In another embodiment, the number of driving related parameters associated with the first event may be more than one, and in this embodiment, information of each driving related parameter may be acquired separately, and then risk level indication information of the first event of the target vehicle may be determined according to the information of each driving related parameter.

In one embodiment of the present application, the respective driving related parameters associated with the lane change event involved in the aggressive driving risk include: at least one of vehicle speed, driving scene, number of continuous lane changes, road gradient, and duration. The duration of continuous driving may refer to a total duration that the vehicle has currently continuously driven.

In one embodiment, based on the real-time speed of the vehicle, it may be determined whether the vehicle is traveling over speed and also the speed of the vehicle when there is a driving risk event.

In one embodiment, the attribute of the road where the vehicle is located may be identified according to the location information (such as longitude and latitude) of the vehicle in combination with the road data acquired in advance. For example, whether the road on which the vehicle is located is an expressway may be identified to determine whether the driving scene of the vehicle is an expressway scene. For example, the front congestion condition (such as whether the vehicle is congested and the congestion degree) of the vehicle on the road where the vehicle is located can be obtained.

In one embodiment, after determining the lane change of the vehicle, it may be determined whether the vehicle is continuously lane-changed by combining the lane change number of the vehicle recorded in a period of time.

In one possible implementation manner, the first lane change in the current period is counted, whether the vehicle changes lanes again in a preset time period (such as 5 minutes, 10 minutes, 15 minutes and the like) can be judged, if the vehicle changes lanes again, the vehicle can be recorded as continuous lane changes, and after each lane change, the corresponding continuous lane change times can be recorded. The larger the number of times of continuous lane change, the larger the corresponding preset score can be, so that the higher the risk score of the current lane change event is, the higher the DD225400I

And accords with the actual risk condition.

In one embodiment, after the lane change of the vehicle is determined, the situation of the front vehicle can be combined to determine whether the distance between the lane change of the vehicle and the front vehicle is closer.

In one embodiment, the longitude and latitude and the altitude reported by the vehicle can be combined to judge whether the vehicle is in a downhill section or not in the process of driving risk event. Referring to fig. 7, the downhill angle can be calculated according to the following formula:

angle x2=math.atan (b/a) 180/math.pi, or angle x2=90 ° -angle x1

Angle x1=math.asin (a/c) 180/math.pi, or angle x1=90 ° -angle x2

Wherein a is the height difference between two altitudes reported by the vehicle, b is the distance between two longitudes and latitudes reported by the vehicle, and b ² ＝c ² -a ² . According to the diagonal principle, the value of the angle x1 can be taken as the downhill angle of the vehicle.

In one embodiment of the present application, the step of obtaining information of each first parameter of the target vehicle may include: in the case where the driving-related parameter associated with the first event includes a running road surface gradient, according to two positioning positions and two altitudes of the target vehicle at two points in time, wherein the positioning positions include longitude and latitude, the two points in time being a start point in time and an end point in time at which the first event exists for the target vehicle; acquiring the distance between two positioning positions; acquiring a height difference value between two altitudes; and obtaining a gradient value of the gradient of the running road surface of the target vehicle associated with the first event according to the distance between the two positioning positions and the height difference between the two altitudes.

Referring to fig. 7, when the vehicle driving road surface is a downhill road surface, the altitude of the vehicle at the starting time point is generally greater than the altitude of the vehicle at the ending time point, the absolute value of the difference between the two may be a shown in fig. 7, and the interval between the two positioning positions may be b shown in fig. 7. In one embodiment, the value of the angle x1 may be calculated according to a and b, where the value of the angle x1 is a slope angle value of the slope road.

In another embodiment, the vehicle can report its altitude, mileage, longitude and latitude in real time. Referring to fig. 7, when the vehicle driving road surface is a downhill road surface, the altitude of the vehicle at the starting time point is generally greater than the altitude of the vehicle at the ending time point, the absolute value of the difference between the altitude and the vehicle may be a shown in fig. 7, the difference obtained by subtracting the mileage at the starting time point from the mileage at the ending time point may be c shown in fig. 7, and the value of the angle x2 may be obtained by calculating according to a and c, thereby obtaining the value of x 1.

In one embodiment of the present application, the time difference between the two time points may also be obtained according to the start time point and the end time point when the first event exists in the target vehicle, and the value of c in fig. 7 may be obtained according to the time difference and the vehicle speed.

In another embodiment of the present application, the step of obtaining information of each first parameter of the target vehicle may include: in the case where the driving-related parameter associated with the first event includes a running road surface gradient, according to two altitudes of the target vehicle at two points in time, the two points in time being a start time point and an end time point at which the first event exists for the target vehicle; acquiring a height difference value between two altitudes; gradient information of a traveling road surface gradient of the target vehicle associated with the first event is obtained from a difference in altitude between the two altitudes.

The altitude difference may be, for example, a value obtained by subtracting the altitude at the start time point from the altitude at the end time point, or may be a value obtained by subtracting the altitude at the start time point from the altitude at the end time point.

Taking the altitude difference as an example of a value obtained by subtracting the altitude at the end time point from the altitude at the start time point, the type of the road surface gradient can be determined from the altitude difference. If the height difference is a positive value, it can be determined that the vehicle is traveling on a downhill road, if the height difference is 0, it can be determined that the vehicle is traveling on a horizontal road, and if the height difference is a negative value, it can be determined that the vehicle is traveling on an uphill road.

In one embodiment, if the height difference is a positive value, the coefficient score of the parameter of the road surface gradient may be greater than 1, if the height difference is 0, the coefficient score of the parameter of the road surface gradient may be equal to 1, and if the height difference is a negative value, the coefficient score of the parameter of the road surface gradient may be less than 1.

In addition, the magnitude of the road gradient can be determined according to the height difference value, and the magnitude of the road gradient and the absolute value of the height difference value form positive correlation.

In one embodiment of the present application, the respective driving related parameters associated with the preceding vehicle approaching event related to the aggressive driving risk include: at least one of distance from the front vehicle, vehicle speed, driving scene, number of times of continuous front vehicle, road gradient of driving and continuous driving duration.

In one embodiment of the present application, the individual driving related parameters associated with the overspeed event involved in aggressive driving risk include: at least one of vehicle speed, driving scene, number of continuous overspeed, road gradient, and duration.

In one embodiment of the present application, the respective driving related parameters associated with the eye-closure event related to the risk of fatigue driving include: at least one of vehicle speed, number of continuous eye closure, road congestion, and duration of driving.

In one embodiment of the present application, the respective driving related parameters associated with the yawing event related to the fatigue driving risk include: at least one of vehicle speed, number of continuous yawning, road congestion condition, and duration of driving.

In one embodiment of the present application, the various driving related parameters associated with the vehicle continuous ignition event related to the risk of fatigue driving include: at least one of vehicle speed, road congestion condition, duration of driving.

Step 103, determining risk degree indication information of a first event of the target vehicle according to the information of each first parameter of the target vehicle.

The risk level indication information of the first event of the target vehicle may be determined from information of all (one or more) preset driving-related parameters of the target vehicle associated with and affecting the risk level of the first event.

In one embodiment of the present application, the risk level indication information of the first event of the target vehicle includes: the risk score of the first event of the target vehicle may indicate the degree of risk by the height of the score. For example, the higher the risk score, the higher the risk level and vice versa.

In one embodiment of the present application, the risk level indication information of the first event at the target vehicle includes: in the case of the risk score of the first event of the target vehicle, the step of determining risk degree indication information of the first event of the target vehicle may include: acquiring a preset score of a first event and a preset score of information of a first parameter of a target vehicle aiming at the first event; taking the product of the obtained preset scores as the risk score of the first event of the target vehicle.

Taking the first event as an eye-closure event, each driving related parameter associated with the eye-closure event includes, for example, a vehicle speed, a number of times of continuous eye closure, a road congestion condition, and a continuous driving duration, a product may be obtained by multiplying the base score and each coefficient score according to a preset score (which may be a base score) of the eye-closure event, and a preset score (which may be a coefficient score) of information of the driving related parameters such as the vehicle speed, the number of times of continuous eye closure, the road congestion condition, and the continuous driving duration with respect to the eye-closure event, and the obtained product may be a risk score of the eye-closure event of the target vehicle.

Considering that the driving related parameters of the driving risk event can cause the risk degree of the driving risk event to be doubly changed, the effect of the doubly changed can be reflected by multiplying the basic score of the driving risk event by the coefficient score of the driving related parameters, and the risk evaluation result obtained in this way can be more in line with the actual risk degree of the driving risk of the vehicle, thereby being beneficial to accurately evaluating the driving risk of the vehicle.

Possibly, the score of different information of the same driving related parameter may be correspondingly different for the same driving risk event. For example, when the number of continuous eye closure times is 0 (i.e., the eye is not closed continuously for a short period of time), the score for the eye closure event may be 1, and when the number of continuous eye closure times is n (n > 0) for a period of time, the score for the eye closure event may be n+1.

For example, assuming that the preset score of the eye-closing event is 10, the vehicle speed is near zero, the continuous eye-closing frequency is 0, the road congestion is congested, the preset score of the eye-closing event for the continuous driving duration is 1h is 0, 1, 0, and 0.5, respectively, the product obtained may be 0=10×0×1×0×0.5, that is, the risk score of the eye-closing event of the target vehicle is 0, and it may be considered that the current eye-closing event is substantially free of risk.

For another example, assuming that the preset score of the eye-closure event is 10, the vehicle speed is 40km/h, the continuous eye-closure number is 3 (which may represent continuous 3 rd eye-closure in a short time), the road congestion is not congested, the preset score of the eye-closure event for the continuous driving duration is 4h is 2, 4, 2, 5, respectively, for example, the obtained product may be 800=10×2×4×2×5, that is, the risk score of the eye-closure event of the target vehicle is 800, and it may be considered that the current eye-closure event is substantially at high risk.

Possibly, the score of the unified information of one driving related parameter for different driving risk events may be correspondingly different. For example, where the score is positively correlated with the risk level, the score for the same vehicle speed value (e.g., 80 km/h) may be greater at eye closure events than at high speed lane change events.

Step 104, obtaining risk degree indicating information of the first driving risk of the target vehicle according to the risk degree indicating information of each first event of the target vehicle.

The risk level indicating information of the first driving risk of the target vehicle may be obtained according to the risk level indicating information of all (one or more) preset first events of the target vehicle. In one embodiment, taking the risk degree indication information of the first event as an example of the risk score of the first event, a sum of the risk scores of the first events of the target vehicle may be calculated, and the risk degree indication information of the first driving risk of the target vehicle may be obtained according to the sum.

In one embodiment, the risk level indicating information of the first driving risk of the target vehicle may be obtained according to the risk level indicating information of each occurrence of the first event of the target vehicle in a period of time. The number of times the first event occurs in the time period may be 0 times, 1 time, or other more times. When the target vehicle makes a first event multiple times within a period of time and the risk degree indication information of the first event is the risk score of the first event, the risk score of each first event may be accumulated as the total risk score of the first event. And further, the total risk score of each first event can be accumulated, so as to obtain risk degree indication information (for example, the risk score) of the first driving risk of the target vehicle.

By adopting a combination mode of addition and multiplication, the event related to the first driving risk and the parameters related to the event are combined, the driving risk condition of the vehicle is judged according to the height of the risk score of the vehicle in a period of time, and the obtained driving risk judging result accords with the actual driving risk condition, so that the accurate judgment of the driving risk of the vehicle can be realized.

Unlike the implementation manner in the prior art that the driving risk of the vehicle is determined only according to the driving risk event (such as the continuous ignition duration of the vehicle, etc.), the embodiment shown in fig. 1 can combine driving related information which is associated with the driving risk event and can affect the risk degree of the driving risk event when the driving risk event occurs to the vehicle, determine the substantial risk degree of the driving risk event occurring to the vehicle based on multidimensional sensing data, and further determine the driving risk of the vehicle according to the substantial risk degree, so that the driving risk of the vehicle can be accurately determined, and the driving safety of the vehicle is facilitated to be ensured.

The embodiment shown in fig. 1 combines the occurrence or non-occurrence of a driving risk event with corresponding driving related information to realize accurate safe driving risk identification based on multidimensional sensing data, and the problem 1 is not existed, so that driving safety risks of some non-high-risk situations can be more effectively identified and removed in a complex scene, and the identification of the driving risk of the vehicle is accurate and efficient. In addition, as the vehicle driving risk identification is realized based on multidimensional sensing data, the driving safety risk can still be identified when a single data source fails or is interfered, and the influence of the problem 2 on the vehicle driving risk identification can be solved. Moreover, the vehicle driving risk identification mode of the embodiment shown in fig. 1 can support different identification requirements of enterprises on risks in different scenes, and the enterprises can conveniently and flexibly adjust according to own requirements.

In one embodiment of the present application, after the risk level indication information of the first driving risk of the target vehicle is obtained, a corresponding level of risk alarm may be performed accordingly, for example, the risk system platform may notify the corresponding vehicle security administrator of the target vehicle through APP, sms, phone, etc.

The embodiment shown in fig. 1 provides an implementation of determining a substantial risk level of a vehicle for occurrence of a driving risk event based on multidimensional sensing data to evaluate a driving risk of the vehicle in combination with driving related information associated with the driving risk event capable of influencing the risk level thereof when the vehicle is at the driving risk event, the implementation may have at least the following features:

1) Data source is diversified, and acquisition is extensive

In the process of finding driving risks, diversified data sources can greatly cover risk driving behaviors in various different scenes. The behavior of the driver is not single, namely, the situation of facial expressions such as eye closure, yawning and the like occurs, the situation that the distance between the front vehicle and the vehicle cannot be effectively controlled, the vehicle cannot effectively run in a road, and even the situation that the vehicle speed cannot be controlled in a downhill road section exists no matter the driver performs the behaviors such as fatigue driving, aggressive driving and the like. The diversified data collection can be a very large overview over the diversified representations described above, helping to obtain more accurate driving risk analysis and judgment to cover the potential risk of safe driving by the driver. Based on multiple data acquisition, risk assessment can be more convinced, and the problem of finding missing of overall risks caused by interference of external factors of single parameters is solved.

2) The risk alarm is independent of a single event, so that the risk alarm is more convincing, and the probability that a plurality of factors are simultaneously interfered is greatly reduced. Whether the fatigue driving behaviors such as overspeed and eye closing exist, certain accidental probability exists, the occurrence of such events does not represent the real risk situation, comprehensive judgment is carried out according to the actual situation, and accurate judgment of the driving risk of the vehicle can be realized. By combining one or more risk parameters associated with a driving risk event, rather than relying on a single event, the possibility of sporadic risk alarms is substantially eliminated algorithmically. For example, according to the conditions of the vehicle speed, downhill slope and the like, corresponding adjustment can be carried out through parameters, for example, when the vehicle is blocked, the yawing under the condition that the vehicle speed is 0 can be considered to have negligible influence on the risk of driving, for example, the distance requirement on the front vehicle in the climbing stage is loosened from the distance requirement on the front vehicle in the downhill stage.

3) The risk assessment scheme can be adjusted as required, for example, the scores of some parameters affecting the risk size can be changed as required, so that personalized customization of different enterprise management requirements can be supported.

In one embodiment of the present application, the risk level indication information of the first event of the target vehicle includes: risk score for a first event of a target vehicle. Based on this, step 104 may include: determining a score range in which a first score falls according to a plurality of preset score ranges corresponding to first driving risks, wherein the score ranges correspond to a plurality of risk grades one by one, and the first score is obtained according to the risk score of each first event of a target vehicle; and taking the risk level corresponding to the score range in which the first score falls as risk level indication information of the first driving risk of the target vehicle.

In one embodiment, the first score may be derived from a risk score for each first event that the target vehicle has occurred during a time period of the current cycle (e.g., 15 minutes, etc.).

In one embodiment, when the number of the first events is one, the risk score of the first event may be the first score. In another embodiment, in a case where the number of first events is more than one, the sum of the risk scores of the respective first events may be regarded as the first score.

In another embodiment, a risk additional value may also be set, where the risk additional value may be a sum of preset scores of various trigger events that occur in the time period of the current period for the target vehicle. When a trigger threshold of a certain type of trigger event is reached, the vehicle may execute the trigger event, and the trigger event may be an alarm reminding event, for example. Based on this, the first score may be a sum of the risk scores of each first event of the target vehicle plus a score obtained by the risk added value.

In one embodiment, a score range that can include individual risk scores that may be expected to exist may be split into multiple ones, resulting in multiple score ranges.

For example, referring to fig. 2-6, the driving risk may have 5 risk levels, i.e., LV 1-LV 5 in fig. 2-6, respectively, and the 5 risk levels may be in one-to-one correspondence with 5 score thresholds. The first score falls into a score threshold, and the risk level corresponding to the score threshold is the current aggressive driving risk information of the vehicle.

In one embodiment of the present application, considering that the eighth rule of the regulations for road traffic safety in the people's republic of China, namely that a motor vehicle runs on an expressway, the speed exceeds 100km/h, a distance of more than 100 meters from a front vehicle on a same lane should be kept, the speed is lower than 100km/h, the distance between the motor vehicle and the front vehicle on the same lane can be properly shortened, but the minimum distance is not less than 50 meters, and the risk during high-speed running and the speed can be known to have positive correlation based on the rule, so that the important reference can be made to the speed during a high-speed lane change (i.e. lane change on the expressway) event and whether the front vehicle exists after the high-speed lane change.

In one possible implementation, the driving risk event related to the aggressive driving risk may include a high-speed lane change event, and to obtain a risk score of the high-speed lane change event, a corresponding risk score calculation model may be constructed, where a score may be given to a driving related parameter related to the high-speed lane change event. Practically, the formula can be: x=a+c+b, and calculating a risk score X of the high-speed lane change event of the vehicle. The basic score of the high-speed lane change event is a, the coefficient score of the vehicle speed during the high-speed lane change is b (for example, when 100km/h is met), and the score of the event with too close vehicle distance after the high-speed lane change is c.

Considering the possibility that a continuous high speed lane change will repeat the high speed lane change risk for a short period of time (e.g., 10 minutes) and will double the risk occurrence, in one possible implementation, the following formula is used: x= (a+c+b) d, and calculating a risk score X of a high-speed lane change event of the vehicle. Where d is the coefficient fraction of the number of consecutive high-speed lane changes. In one embodiment, b may be a coefficient fraction of the average or maximum of the speed of each high speed lane change when the speed of the different high speed lane changes is different.

Considering that the strategies adopted by vehicles in the ascending and descending of the slopes are different, for example, when the vehicles ascend the slopes, in order to ensure that the vehicle distance can properly accelerate to step on the accelerator, when the vehicles descend the slopes, if the vehicle distance needs to be kept to be properly braked, if the high-speed lane change event occurs in the descending of the slopes, the possibility of occurrence of the risk is greatly increased, and in one possible implementation, the following formula is adopted: x= (a+c+b) d e, and calculating a risk score X of the high-speed lane change event of the vehicle. Wherein d is the coefficient fraction of the continuous high-speed lane change times, and the downhill coefficient fraction is e. In one embodiment, b may be a coefficient fraction of the average or maximum downhill slope value for each high speed lane change slope when the slopes of the different high speed lanes are different.

If various alarm events occur for a plurality of times within a period of time, the driver not only can be indicated to have a tendency of driving in an exciting way, but also can be indicated to have a slight awareness of the driver on safe driving. Special attention may be given to the fact that an offending event continues to occur under the cues of multiple device local alarms. In this way, in one possible implementation manner, a risk additional value f may also be set, where the risk additional value f may be a sum of preset scores of various triggering events that occur in the time period of the current cycle. Based on this, the formula can be: x= (a X b + c X b) d X e + f calculates a risk score X of a high speed lane change event of the vehicle. Wherein d is a coefficient score of the number of continuous high-speed lane change, the coefficient score of the downhill is e, and the score of multiple alarms occurring within a period of time (such as 10 minutes) is f.

It can be seen that in one embodiment, for high speed lane change events involving aggressive driving risk, the main potential safety hazard points that can be of concern may be: high-speed lane change event, speed condition during high-speed lane change, event of too close a front vehicle after high-speed lane change, frequent occurrence of high-speed lane change for many times in a short period, downhill condition during high-speed lane change, and the like.

If the score X is found to be reached within Y minutes, the vehicle is considered to have a certain risk of driving by the shock, and the level of the risk of driving by the shock can be set according to the score X. If 100 minutes are reached, the aggressive driving risk level is 1, if 200 minutes are reached, the aggressive driving risk level is 2, and so on. Wherein, a plurality of grades can be set, and the plurality of grades respectively correspond to a plurality of score intervals.

It is possible to set a plurality of (e.g., 5) different levels of aggressive driving levels, with the score ranges of the different aggressive driving levels being correspondingly different. Taking the score of X in a period of time (such as 10 minutes), and obtaining the current aggressive driving risk level of the vehicle according to the score range of the X.

In one embodiment, a higher level of aggressive driving level may mean that the speed of the high speed lane change is faster, the high speed lane change occurs during downhill grades, and the risk factor increases multiple times. In practical application, enterprises can adjust specific values of basic scores and coefficient scores according to own needs, and the algorithm mode of X can not be adjusted.

In one embodiment of the present application, the risk level indication information of the first event of the target vehicle includes: risk score for a first event of a target vehicle. Based on this, step 104 may include: comparing the second score with a preset score threshold under the condition that the first driving risk is fatigue driving risk, wherein the second score is obtained according to the risk score of each first event of the target vehicle, and the risk score is positively related to the risk degree; under the condition that the second score is larger than the score threshold value, acquiring first information, wherein the first information is used for indicating information of at least one alarm event of a front vehicle approaching alarm, a front vehicle collision alarm and a pedestrian approaching alarm of the target vehicle in an associated time period of the first event of the target vehicle; and obtaining risk degree indicating information of the first driving risk of the target vehicle according to the first information and the second score.

In one embodiment, the score threshold may be 0. The second score may typically take on a value of 0 or greater than 0. And when the second score is 0, the fatigue driving risk of the vehicle is not shown, otherwise, the fatigue driving risk of the vehicle is shown.

After determining that the second score is greater than the score threshold, that is, determining that the fatigue driving risk exists in the vehicle, the first information can be obtained, and the risk level of the fatigue driving risk of the vehicle can be obtained according to the first information and the second score, so that the fatigue driving risk can be accurately evaluated.

Considering that the distance (such as 100 m) between the vehicle and the front vehicle is generally larger than the distance (such as 40 m) between the vehicle and the front vehicle when the front vehicle collides and the distance (such as 50 m) between the vehicle and the pedestrian when the pedestrian is in too close alarm, the driving risk when the vehicle is in the vehicle to be close alarm is generally smaller than the driving risk when the vehicle is in the front vehicle collides and the pedestrian is in the pedestrian to be too close alarm, the loss possibly caused by the front vehicle to be close alarm is generally smaller than the loss possibly caused by the front vehicle collides and the pedestrian is too close alarm, the risk of the front vehicle collision and the risk of the pedestrian to be too close alarm can be further caused, the loss is reproduced, the risk of the front vehicle collision and the risk of the pedestrian to be too close alarm can be used as basic scores, and the scores of the front vehicle collision and the pedestrian to be too close alarm can be used as coefficient scores. Based on this, in one embodiment, the formula for calculating the risk score for the fatigue driving risk of the vehicle may be:

DD225400I

X＝A+g+A*h+A*i

Wherein X is the risk score of fatigue driving risk of the vehicle, A is the second score, g is the preset score of the near warning of the front vehicle, h is the preset score of the collision warning of the front vehicle, and i is the preset score of the pedestrian approaching warning.

The risk of the fatigue driving risk of the vehicle can be properly increased through the basic score of the vehicle approaching alarm, the on-demand multiple-amplification effect of the fatigue driving risk of the vehicle can be realized through the coefficient score of the front vehicle collision alarm and the pedestrian approaching alarm, and the obtained risk assessment result can be more in line with the actual risk degree of the driving risk of the vehicle, so that the accurate assessment of the driving risk of the vehicle is facilitated.

The risk score X and the plurality of preset score ranges may be used as a risk level of the fatigue driving risk of the vehicle according to a preset risk level corresponding to the score range in which the risk score X falls.

In one embodiment of the present application, consider the rule "driving a motor vehicle must not have the following behavior" by the sixty two lines of regulations of the national road traffic safety law: (seventh) continuously driving the motor vehicle for more than 4 hours without stopping the motor vehicle for rest or with the stopping time being less than 20 minutes, "the motor vehicle driver should comply with the rules of road traffic safety laws and regulations, safe driving according to the operation specification and civilized driving" in twenty-second rule of the national road traffic safety law of people's republic of China; the method comprises the steps of drinking wine, taking mental medicines or narcotics regulated by the country, or suffering from diseases which prevent safe driving of motor vehicles, or excessively fatiguing to influence safe driving, and not driving motor vehicles, wherein the 'technical guidelines for evidence obtaining of traffic offence of fatigue driving' issued by the public security department traffic authorities clearly have evidence to prove that the situation that a driver cannot stop and rest in time due to objective reasons such as road traffic accidents, traffic jams, bad weather and the like is caused when the driver stays on the road for a long time in a suspected fatigue driving time period, and the fatigue driving is not considered, and based on the regulations, the continuous driving is known to have high risk of occurrence of the fatigue driving for 4 hours and is easy to cause illegal behaviors by the driver when the driver cannot stop and rest in time due to congestion, traffic accidents and the like at the moment, and the fatigue driving is not considered.

In one possible implementation, the driving risk event related to the fatigue driving risk may include a closed-eye yawing event (such as a closed-eye yawing event and/or a yawing event), and to obtain a risk score of the closed-eye yawing event, a corresponding risk score calculation model may be constructed, where a score may be given to a driving related parameter related to the closed-eye yawing event. Practically, the formula can be: a=a×c+b×c, and calculating a risk score a of a closed-eye yawning event of the vehicle. The score of the closed-eye yawing event is a, the score of the yawing event is b, and the coefficient score of the vehicle speed when the closed-eye yawing event occurs is c.

In one possible implementation, when the vehicle speed is below 30km/h, 30-80km/h and above 80km/h, the value of c can be three coefficient fractions of 0, 1 and 2 respectively.

Considering that the fatigue driving risk can be related to road congestion and the duration of driving of the driver, in one possible implementation, the following formula is used: a= (a×c+b×c) ×d×e, and calculating a risk score a of the closed-eye yawning event of the vehicle. The coefficient score of the road congestion condition is d, and the coefficient score of the continuous driving duration is e.

In one possible implementation manner, the road congestion condition of the vehicle at the moment can be obtained according to the longitude and latitude of the vehicle when the eye closing and yawning events occur. The d value may be fixed to 0 and 1, for example, d is 0 in a congested road segment, and d is 1 in a non-congested road segment.

In one possible implementation, the duration e is 0 within 4 hours, and the duration e may be set to a value of 1 or higher above 4 hours, for example, the risk factor may increase exponentially with the duration.

Thus, when an event of closed-eye yawing occurs, if the speed of the vehicle is lower than 30km/h when the event occurs, or the vehicle is in a congested road section, or the duration of driving is less than 4 hours, the occurrence of the closed-eye yawing event can not be considered to cause fatigue driving risk.

Considering the possibility that continuous eye closure, yawning, and repeated fatigue driving risks in a short period of time (e.g., 10 minutes) and multiple increases the risk, in one possible implementation, the following formula is used: a= (a×c+b×c) ×d×e×f, and calculating a risk score a of a closed-eye yawning event of the vehicle. Where f is a coefficient fraction of the number of times a closed-eye yawning event occurs in succession.

When a+.0, it can be considered that there is a risk of fatigue driving. Considering that the direct hazard mainly caused by fatigue driving is rear-end collision of a vehicle, when the vehicle is too close to the vehicle, collision early warning is needed to be carried out, and high precaution is needed. Based on this, after determining that a+.0, it is possible to continue paying attention to the continuous driving duration of the vehicle, whether there is a vehicle-distance approaching event, a front-vehicle collision warning, a pedestrian approaching warning. The vehicle approaching alarm can be an auxiliary alarm generally, and the front vehicle collision alarm and the pedestrian approaching alarm can all calculate the alarm within 50m according to the vehicle speed according to each local standard, namely, the type of alarm is less than 50 meters with a collision target object when the type of alarm occurs.

In one possible implementation, the following formula may be used: x=if (a+note0) =a+g+a+h+a+i, and update and adjust the risk score of the closed-eye yawning event of the vehicle. The basic score of the vehicle distance approaching alarm is g, the coefficient score of the front vehicle collision alarm is h, and the coefficient score of the pedestrian approaching alarm is i.

It can be seen that in one embodiment, for a closed-eye yawning event related to fatigue driving risk, the main potential safety hazard points that can be focused on may be: an eye closing event, a yawning event, a vehicle speed condition when closing eyes, a vehicle speed condition when yawning, a time period when closing eyes, a time period when yawning, a continuous driving duration, a vehicle distance approaching event, a front vehicle collision alarm, a pedestrian approaching alarm and the like.

It is possible to set a plurality of (e.g. 3) different levels of fatigue driving levels, the score ranges of which are correspondingly different. For different fatigue driving grades, a higher level can mean that the fatigue degree of a driver is high, the fatigue characteristic is obvious, and the driver needs to rest immediately. The score of X in a period of time (such as 10 minutes and 15 minutes) can be taken, and the current fatigue driving risk level of the vehicle is obtained according to the score range of the X.

Based on the vehicle driving risk information acquisition mode provided by any embodiment of the application, risk discovery of factors such as fatigue driving, aggressive driving, and severe environment driving risk of a driver can be realized through different kinds of risk models formed by pre-combining.

As shown in fig. 8, an embodiment of the present application provides a vehicle driving risk information acquisition apparatus 80, including: the monitoring module 801 is configured to monitor, for each first event related to the first driving risk, whether the target vehicle has the first event; the first obtaining module 802 is configured to obtain, when it is detected that the target vehicle has a first event, information of first parameters of the target vehicle, where the first parameters are driving related parameters associated with the first event, and the first parameters affect a risk level of the first event; the determining module 803 is configured to determine risk level indication information of a first event of the target vehicle according to information of each first parameter of the target vehicle; the second obtaining module 804 is configured to obtain risk level indication information of a first driving risk of the target vehicle according to risk level indication information of each first event of the target vehicle.

One embodiment of the present application provides an electronic chip, including: a processor for executing computer program instructions stored on a memory, wherein the computer program instructions, when executed by the processor, trigger the electronic chip to perform the method as described in any of the embodiments of the present application.

An embodiment of the present application provides an electronic device comprising a memory for storing computer program instructions, a processor for executing the computer program instructions, and a communication means, wherein the computer program instructions, when executed by the processor, trigger the electronic device to perform a method as described in any of the embodiments of the present application.

An embodiment of the present application provides a computer-readable storage medium having a computer program stored therein, which when run on a computer, causes the computer to perform the method of any of the embodiments of the present application.

An embodiment of the present application provides a computer program product comprising a computer program which, when run on a computer, causes the computer to perform the method as described in any of the embodiments of the present application.

Fig. 9 is a schematic diagram of a computer device according to an embodiment of the present application. As shown in fig. 9, the computer device 20 of this embodiment includes: the processor 21 and the memory 22, the memory 22 is used for storing a computer program 23 that can run on the processor 21, and the computer program 23 when executed by the processor 21 implements the steps in the method embodiments of the present application, so that repetition is avoided, and details are not repeated here. Alternatively, the computer program 23, when executed by the processor 21, performs the functions of the models/units in the embodiments of the apparatus of the present application, and in order to avoid repetition, it is not described in detail herein.

Computer device 20 includes, but is not limited to, a processor 21 and a memory 22. It will be appreciated by those skilled in the art that fig. 9 is merely an example of the computer device 20 and is not intended to limit the computer device 20, and may include more or fewer components than shown, or may combine certain components, or different components, e.g., the computer device may further include an input-output device, a network access device, a bus, etc.

The processor 21 may be a central processing unit (Central Processing Unit, CPU), but may also be other general purpose processors, digital signal processors (Digital Signal Processor, DSP), application specific integrated circuits (Application specific Integrated Circuit, ASIC), field programmable gate arrays (Field-Programmable Gate Array, FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, or the like. A general purpose processor may be a microprocessor, or the processor may be any conventional processor or the like.

The memory 22 may be an internal storage unit of the computer device 20, such as a hard disk or memory of the computer device 20. The memory 22 may also be an external storage device of the computer device 20, such as a plug-in hard disk, smart Media (SM) card, secure Digital (SD) card, flash card (FlashCard) or the like, which are provided on the computer device 20. Further, the memory 22 may also include both internal and external storage units of the computer device 20. The memory 22 is used to store a computer program 23 and other programs and data required by the computer device. The memory 22 may also be used to temporarily store data that has been output or is to be output.

In the several embodiments provided in this application, it should be understood that the disclosed systems, devices, and methods may be implemented in other manners. For example, the apparatus embodiments described above are merely illustrative, e.g., the division of the elements is merely a logical function division, and there may be additional divisions when actually implemented, e.g., multiple elements or components may be combined or integrated into another system, or some features may be omitted or not performed. Alternatively, the coupling or direct coupling or communication connection shown or discussed with each other may be an indirect coupling or communication connection via some interfaces, devices, or units, which may be in electrical, mechanical, or other forms.

The units described as separate units may or may not be physically separate, and units shown as units may or may not be physical units, may be located in one place, or may be distributed over a plurality of network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

In addition, each functional unit in each embodiment of the present application may be integrated in one processing unit, or each unit may exist alone physically, or two or more units may be integrated in one unit. The integrated units may be implemented in hardware or in hardware plus software functional units.

The integrated units, implemented in the form of software functional units, may be stored in a computer readable storage medium. The software functional unit is stored in a storage medium, and includes several instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) or a Processor (Processor) to perform part of the steps of the methods described in the embodiments of the present application. And the aforementioned storage medium includes: a U-disk, a removable hard disk, a Read-Only Memory (ROM), a random access Memory (Random Access Memory, RAM), a magnetic disk, or an optical disk, or other various media capable of storing program codes.

In the present embodiments, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising one … …" does not exclude the presence of other like elements in a process, method, article or apparatus that comprises the element.

The application may be described in the general context of computer-executable instructions, such as program modules, being executed by a computer. Generally, program modules include routines, programs, objects, components, data structures, etc. that perform particular tasks or implement particular abstract data types. The application may also be practiced in distributed computing environments where tasks are performed by remote processing devices that are linked through a communications network. In a distributed computing environment, program modules may be located in both local and remote computer storage media including memory storage devices.

All embodiments in the application are described in a progressive manner, and identical and similar parts of all embodiments are mutually referred, so that each embodiment mainly describes differences from other embodiments. In particular, for the device embodiments, since they are substantially similar to the method embodiments, the description is relatively simple, and reference is made to the description of the method embodiments in part.

Those of ordinary skill in the art will appreciate that the various elements and algorithm steps described in connection with the embodiments disclosed herein may be implemented as a combination of electronic hardware, computer software, and electronic hardware. Whether such functionality is implemented as hardware or software depends upon the particular application and design constraints imposed on the solution. Skilled artisans may implement the described functionality in varying ways for each particular application, but such implementation decisions should not be interpreted as causing a departure from the scope of the present application.

It will be clear to those skilled in the art that, for convenience and brevity of description, specific working procedures of the above-described systems, apparatuses and units may refer to corresponding procedures in the foregoing method embodiments, and are not repeated herein.

The foregoing description of the preferred embodiments of the present invention is not intended to limit the invention to the precise form disclosed, and any modifications, equivalents, improvements and alternatives falling within the spirit and principles of the present invention are intended to be included within the scope of the present invention.

Claims

1. A vehicle driving risk information acquisition method, characterized by comprising:

for each first event related to a first driving risk, monitoring whether the first event exists in the target vehicle;

acquiring information of each first parameter of the target vehicle under the condition that the first event exists in the target vehicle, wherein the first parameter is a driving related parameter associated with the first event and affects the risk degree of the first event;

determining risk degree indication information of the first event of the target vehicle according to information of each first parameter of the target vehicle;

And obtaining risk degree indicating information of the first driving risk of the target vehicle according to the risk degree indicating information of each first event of the target vehicle.

2. The method of claim 1, wherein the risk level indicative of the first event of the target vehicle comprises: a risk score for the first event of the target vehicle;

the obtaining risk degree indicating information of the first driving risk of the target vehicle according to the risk degree indicating information of each first event of the target vehicle includes:

determining a score range in which a first score falls according to a plurality of preset score ranges corresponding to the first driving risk, wherein the score ranges correspond to a plurality of risk grades one by one, and the first score is obtained according to the risk score of each first event of the target vehicle;

and taking the risk level corresponding to the score range in which the first score falls as risk level indication information of the first driving risk of the target vehicle.

3. The method of claim 1, wherein the risk level indicative of the first event of the target vehicle comprises: a risk score for the first event of the target vehicle;

The determining risk level indication information of the first event of the target vehicle includes:

acquiring a preset score of the first event and a preset score of information of the first parameter of the target vehicle aiming at the first event;

taking the product of the obtained preset scores as a risk score of the first event of the target vehicle.

4. The method according to claim 1, wherein, in case the first driving risk is a aggressive driving risk, the first event to which the first driving risk relates comprises: at least one of lane change event, front vehicle approaching event and overspeed event;

the event that the front vehicle is close indicates that the distance between the vehicle and the front vehicle is smaller than a preset distance threshold value;

the respective driving related parameters associated with the lane change event involved in the aggressive driving risk include: at least one of vehicle speed, driving scene, number of continuous lane change, road gradient, and duration;

the respective driving related parameters associated with the preceding vehicle approaching event related to the aggressive driving risk include: at least one of distance from the front vehicle, vehicle speed, driving scene, number of times of continuous front vehicle, road gradient of driving and continuous driving duration;

The individual driving related parameters associated with the overspeed event related to the aggressive driving risk include: at least one of vehicle speed, driving scene, number of continuous overspeed, road gradient, and duration.

5. The method according to claim 1 or 4, wherein the acquiring information of the respective first parameters of the target vehicle includes:

in the case where the driving-related parameter associated with the first event includes a running road surface gradient, according to two positioning positions and two altitudes of the target vehicle at two points in time, wherein the positioning positions include longitude and latitude, the two points in time being a start time point and an end time point at which the first event exists in the target vehicle;

acquiring the distance between the two positioning positions;

acquiring a height difference value between the two altitudes;

and obtaining a gradient value of the gradient of the running road surface of the target vehicle associated with the first event according to the distance between the two positioning positions and the height difference between the two altitudes.

6. The method according to claim 1, wherein, in case the first driving risk is a fatigue driving risk, the first event related to the first driving risk comprises: at least one of an eye closure event, a yawning event, a vehicle continuous ignition event;

The respective driving related parameters associated with the eye-closure event related to the fatigue driving risk include: at least one of vehicle speed, number of continuous eye closure, road congestion, and duration of driving;

the respective driving related parameters associated with the yawing event related to the fatigue driving risk include: at least one of vehicle speed, number of continuous yawing, road congestion condition and continuous driving duration;

the respective driving related parameters associated with the vehicle consecutive ignition event related to the fatigue driving risk include: at least one of vehicle speed, road congestion condition, duration of driving.

7. The method of claim 1, wherein the risk level indicative of the first event of the target vehicle comprises: a risk score for the first event of the target vehicle;

comparing a second score with a preset score threshold under the condition that the first driving risk is fatigue driving risk, wherein the second score is obtained according to the risk score of each first event of the target vehicle, and the risk score is positively related to the risk degree;

Acquiring first information when the second score is greater than the score threshold value, wherein the first information is used for indicating that the target vehicle has at least one of the information of the alarm event of the approaching front vehicle alarm, the collision alarm of the front vehicle and the approaching pedestrian alarm in the associated time period of the first event of the target vehicle;

and obtaining risk degree indicating information of the first driving risk of the target vehicle according to the first information and the second score.

8. A vehicle driving risk information acquisition apparatus, characterized by comprising:

a monitoring module for monitoring, for each first event related to a first driving risk, whether the first event exists in the target vehicle;

a first obtaining module, configured to obtain information of each first parameter of the target vehicle when the first event exists in the target vehicle, where the first parameter is a driving related parameter associated with the first event, and the first parameter affects a risk degree of the first event;

a determining module, configured to determine risk level indication information of the first event of the target vehicle according to information of each first parameter of the target vehicle;

The second acquisition module is used for acquiring risk degree indicating information of the first driving risk of the target vehicle according to the risk degree indicating information of each first event of the target vehicle.

9. An electronic device comprising a memory for storing computer program instructions, a processor for executing the computer program instructions, and communication means, wherein the computer program instructions, when executed by the processor, trigger the electronic device to perform the method of any of claims 1-7.

10. A computer readable storage medium, characterized in that the computer readable storage medium has stored therein a computer program which, when run on a computer, causes the computer to perform the method according to any of claims 1-7.