Vehicle driving risk analysis method and related device based on artificial intelligence

By obtaining vehicle driving information, partition belt type and lane type, the initial driving risk information is corrected, and the problem of insufficient consideration of vehicle environmental factors in the prior art is solved, and the accuracy and reliability of vehicle driving risk analysis is improved.

CN111739288BActive Publication Date: 2024-11-22TENCENT TECHNOLOGY (SHENZHEN) CO LTD
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202010443691.8
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2020-05-22
Publication Date
2024-11-22
Estimated Expiration
2040-05-22

AI Technical Summary

Technical Problem

The existing AI-based vehicle driving risk analysis method has low accuracy when considering vehicle environmental factors, resulting in limited reliability.

Method used

By obtaining vehicle driving information, partition belt type and lane type, using correction information to correct initial driving risk information, and generating final driving risk information to improve the accuracy and reliability of the analysis.

Benefits of technology

It effectively improves the accuracy of vehicle driving risk analysis, ensures the reliability of artificial intelligence-based driving risk analysis, and can more accurately evaluate the driving risk of vehicles in road environments.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN111739288B_ABST
    Figure CN111739288B_ABST
Patent Text Reader

Abstract

The present application provides a vehicle driving risk analysis method and related devices based on artificial intelligence, which belongs to the field of vehicle networking technology. The method includes: obtaining vehicle driving information of a first vehicle and a second vehicle on a road; inputting the vehicle driving information into a driving risk analysis model to obtain initial risk information; obtaining the type of the dividing strip of the dividing strip on the road, and obtaining the lane type of the second vehicle relative to the first vehicle; obtaining correction information corresponding to the dividing strip type and the lane type, and using the correction information to correct the initial driving risk information to obtain the final driving risk information. The embodiments of the present application effectively improve the accuracy of vehicle driving risk analysis and ensure the reliability of vehicle driving risk analysis based on artificial intelligence.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present application relates to the field of vehicle networking technology, and more specifically, to an artificial intelligence-based vehicle driving risk analysis method and related devices. Background Art

[0002] With the development of technologies such as autonomous driving, safety assisted driving, and vehicle-road collaboration, the analysis of vehicle driving risks is critical. Accurate analysis of vehicle driving risks is of great significance for the implementation of technologies such as autonomous driving, safety assisted driving, and vehicle-road collaboration. At present, there are methods based on artificial intelligence to analyze the driving risks of vehicles by analyzing the driving intentions between vehicles, for example, analyzing the driving risks of vehicles by analyzing the status of the driver. However, insufficient consideration of environmental factors when the vehicle is driving on the road leads to low accuracy in vehicle driving risk analysis, which limits the reliability of vehicle driving risk analysis based on artificial intelligence.

[0003] It should be noted that the information disclosed in the above background technology section is only used to enhance the understanding of the background of the present disclosure, and therefore may include information that does not constitute the prior art known to ordinary technicians in the field. Summary of the invention

[0004] The purpose of the embodiments of the present application is to provide a vehicle driving risk analysis method and device based on artificial intelligence, which can effectively improve the accuracy of vehicle driving risk analysis and ensure the reliability of vehicle driving risk analysis based on artificial intelligence.

[0005] According to one embodiment of the present application, a vehicle driving risk analysis method based on artificial intelligence may include: obtaining vehicle driving information of a first vehicle and a second vehicle on a passable road; inputting the vehicle driving information into a driving risk analysis model to obtain initial risk information of driving risk caused by the second vehicle to the first vehicle; obtaining a dividing strip type of a dividing strip on the passable road, and obtaining a lane type of the second vehicle relative to the first vehicle, the lane type indicating the relative positions of the lane where the second vehicle is located and the lane where the first vehicle is located on both sides of the dividing strip; obtaining correction information corresponding to the dividing strip type and the lane type, and using the correction information to correct the initial driving risk information to obtain final driving risk information of driving risk caused by the second vehicle to the first vehicle.

[0006] According to one embodiment of the present application, a vehicle driving risk analysis device based on artificial intelligence may include: a first acquisition module, used to obtain vehicle driving information of a first vehicle and a second vehicle on a passing road; a pre-analysis module, used to input the vehicle driving information into a driving risk analysis model to obtain initial risk information of driving risk caused by the second vehicle to the first vehicle; a second acquisition module, used to obtain the type of dividing strip of the dividing strip on the passing road, and obtain the lane type of the second vehicle relative to the first vehicle, the lane type indicating the relative position of the lane where the second vehicle is located and the lane where the first vehicle is located on both sides of the dividing strip; a correction module, used to obtain correction information corresponding to the dividing strip type and the lane type, and use the correction information to correct the initial driving risk information to obtain the final driving risk information of driving risk caused by the second vehicle to the first vehicle.

[0007] In some embodiments of the present application, the second acquisition module is configured to: acquire a road image including an image of a dividing strip on the passable road; input the road image into a type determination model to obtain a dividing strip type of the dividing strip on the passable road, the dividing strip type including a first type and a second type, the first type indicating a dividing strip that cannot collide and block vehicles, and the second type indicating a dividing strip that can collide and block vehicles.

[0008] In some embodiments of the present application, the second acquisition module is configured to: when the dividing strip type is the second type, obtain a first occurrence rate of a first accident and a second occurrence rate of a second accident on the pass road, the first accident being a traffic accident in which a vehicle does not cross the dividing strip after colliding with the dividing strip, and the second accident being a traffic accident in which a vehicle crosses the dividing strip after colliding with the dividing strip; based on the first occurrence rate and the second occurrence rate, determine a subtype of the second type as the dividing strip type.

[0009] In some embodiments of the present application, the second acquisition module is configured to: calculate the first probability that the vehicle cannot cross the dividing strip according to the formula T1=p1 / (p1+p2), wherein T1 is the first probability, p1 is the first occurrence rate, and p2 is the second occurrence rate; compare the first probability with the first probability threshold, and determine the subtype of the second type as the dividing strip type, wherein the first probability threshold is used to divide at least two probability ranges, and the probability ranges are the probability ranges that the vehicle cannot cross the dividing strip, and the probability ranges correspond to different subtypes respectively.

[0010] In some embodiments of the present application, the second acquisition module is configured to: obtain the first average mass of the vehicle in the first accident and the first average speed of the vehicle when it hits the dividing strip; obtain the second average mass of the vehicle in the second accident and the second average speed of the vehicle when it hits the dividing strip; calculate the second probability that the vehicle cannot cross the dividing strip according to the formula T2=(m1*v1*p1) / (m1*v1*p1+m2*v2*p2)), where T2 is the second probability, p1 is the first occurrence rate, m1 is the first average mass, v1 is the first average speed, p2 is the second occurrence rate, m2 is the second average mass, and v2 is the second average speed; compare the second probability with the second probability threshold, and determine the subtype of the second type as the dividing strip type, where the second probability threshold is used to divide at least two probability ranges, the probability ranges are the probability ranges that the vehicle cannot cross the dividing strip, and the probability ranges correspond to different subtypes respectively.

[0011] In some embodiments of the present application, the correction module is configured to: search for a correction factor corresponding to both the separation strip type and the lane type from a preset correction factor mapping table;

[0012] The initial driving risk value is corrected using the correction factor to obtain a final driving risk value of the driving risk caused by the second vehicle to the first vehicle.

[0013] In some embodiments of the present application, the lane type includes a same-side same-direction lane and an opposite-side reverse lane; the subtype includes a first subtype and a second subtype, and the probability range corresponding to the first subtype is higher than the probability range corresponding to the second subtype. The correction module is configured as follows: when the dividing strip type is the first type and the lane type is the same-side same-direction lane, the initial driving risk value is corrected according to the formula E=E1*(1+p0); when the dividing strip type is the first type and the lane type is the opposite-side reverse lane, the initial driving risk value is corrected according to the formula E=E1*(1-p0); when the dividing strip type is the first subtype and the lane type is the same-side same-direction lane, the initial driving risk value is corrected according to the formula E=E1+E1*p1 / (p1+p2) / S. driving risk value; when the dividing strip type is the first subtype and the lane type is the opposite-side reverse lane, the initial driving risk value is corrected according to the formula E=E1*p2 / (p1+p2) / S; when the dividing strip type is the second subtype and the lane type is the same-side same-direction lane, the initial driving risk value is corrected according to the formula E=E1+E1*p1 / (p1+p2) / J; when the dividing strip type is the second subtype and the lane type is the opposite-side reverse lane, the initial driving risk value is corrected according to the formula E=E1*p2 / (p1+p2) / J; wherein E is the final driving risk value, E1 is the initial driving risk value, p0 is the first correction factor, S is the second correction factor, and J is the third correction factor, and the second correction factor is greater than the third correction factor.

[0014] In some embodiments of the present application, the warning module is also configured to: generate vehicle warning information according to the final driving risk information; and use the first vehicle to output the vehicle warning information to provide a driving risk warning for the first vehicle.

[0015] According to another embodiment of the present application, an electronic device may include: a memory storing computer-readable instructions; and a processor reading the computer-readable instructions stored in the memory to execute the method described above.

[0016] According to another embodiment of the present application, a computer program medium stores computer-readable instructions, and when the computer-readable instructions are executed by a processor of a computer, the computer is caused to execute the method described above.

[0017] According to the embodiment of the present application, the initial risk information of the driving risk caused by the second vehicle to the first vehicle can be preliminarily analyzed by using the vehicle driving information of the first vehicle and the second vehicle through the driving risk analysis model; then, by obtaining the type of the dividing strip of the dividing strip on the road, and obtaining the lane type can indicate the relative position of the lanes where the two vehicles are located on both sides of the dividing strip, the influence of the dividing strip on the road on the driving risk can be further considered; then, by obtaining the correction information corresponding to the dividing strip type and the lane type, the initial driving risk information is corrected to obtain the final driving risk information of the driving risk caused by the second vehicle to the first vehicle. The dividing strip type and the lane type can accurately reflect the influence of the first vehicle and the second vehicle on the driving risk due to the introduction of the dividing strip on the current road, effectively consider the influence of the dividing strip on the road on the driving risk, effectively improve the accuracy of the vehicle driving risk analysis, and ensure the reliability of the vehicle driving risk analysis based on artificial intelligence.

[0018] Other features and advantages of the present application will become apparent from the following detailed description in conjunction with the accompanying drawings, or may be partially learned through the practice of the present application.

[0019] It is to be understood that both the foregoing general description and the following detailed description are exemplary and explanatory only and are not intended to restrict the present application. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] Figure 1 A schematic diagram of a system to which the embodiments of the present application can be applied is shown.

[0021] Figure 2 A flow chart of a vehicle driving risk analysis method based on artificial intelligence according to an embodiment of the present application is shown.

[0022] Figure 3 A flow chart of a method for obtaining a separation zone type according to an embodiment of the present application is shown.

[0023] Figure 4 A flowchart of a method for obtaining a separation zone type according to yet another embodiment of the present application is shown.

[0024] Figure 5 A flowchart of a method for obtaining a separation zone type according to yet another embodiment of the present application is shown.

[0025] Figure 6 A flowchart of a method for obtaining a separation zone type according to yet another embodiment of the present application is shown.

[0026] Figure 7 A flow chart of a method for correcting an initial driving risk value according to an embodiment of the present application is shown.

[0027] Figure 8A flowchart of a method for correcting an initial driving risk value according to yet another embodiment of the present application is shown.

[0028] Fig. 9 A block diagram of an artificial intelligence-based vehicle driving risk analysis device according to an embodiment of the present application is shown.

[0029] Fig.10 A block diagram of an electronic device according to an embodiment of the present application is shown. DETAILED DESCRIPTION

[0030] Example embodiments will now be described more fully with reference to the accompanying drawings. However, example embodiments can be implemented in a variety of forms and should not be construed as limited to the examples set forth herein; rather, these embodiments are provided so that this application will be more comprehensive and complete and fully convey the concept of the example embodiments to those skilled in the art.

[0031] In addition, described feature, structure or characteristic can be combined in one or more embodiments in any suitable manner. In the following description, many specific details are provided to provide a full understanding of the embodiments of the present application. However, those skilled in the art will appreciate that the technical scheme of the present application can be put into practice without one or more of the specific details, or other methods, components, devices, steps, etc. can be adopted. In other cases, known methods, devices, realizations or operations are not shown or described in detail to avoid blurring the various aspects of the application.

[0032] The block diagrams shown in the accompanying drawings are merely functional entities and do not necessarily correspond to physically independent entities. That is, these functional entities may be implemented in software form, or in one or more hardware modules or integrated circuits, or in different networks and / or processor devices and / or microcontroller devices.

[0033] The flowcharts shown in the accompanying drawings are only exemplary and do not necessarily include all the contents and operations / steps, nor must they be executed in the order described. For example, some operations / steps can be decomposed, and some operations / steps can be combined or partially combined, so the actual execution order may change according to actual conditions.

[0034] Figure 1 A schematic diagram of a system 100 to which the embodiments of the present application can be applied is shown.

[0035] like Figure 1 As shown, the system 100 may include a cloud server 101 , a traffic management department server 102 , a vehicle terminal 103 , a vehicle terminal 104 , a vehicle terminal 105 , and a vehicle terminal 106 .

[0036] The cloud server 101 and the traffic management department server 102 can be independent physical servers, or a server cluster or distributed system composed of multiple physical servers. They can also be cloud servers that provide basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communications, middleware services, domain name services, security services, CDN, as well as big data and artificial intelligence platforms.

[0037] In particular, in the real-time mode of this example, the cloud server 101 can provide artificial intelligence cloud services. The so-called artificial intelligence cloud services are generally referred to as AIaaS (AIasaService, Chinese for "AI as a Service"). This is a mainstream service mode of an artificial intelligence platform. Specifically, the AIaaS platform will split several common AI services and provide independent or packaged services in the cloud. This service model is similar to opening an AI theme mall: all developers can access and use one or more artificial intelligence services provided by the platform through API interfaces. Some senior developers can also use the AI ​​framework and AI infrastructure provided by the platform to deploy and operate their own cloud artificial intelligence services. For example, vehicles on the road can implement vehicle driving risk analysis based on artificial intelligence based on the artificial intelligence cloud service provided by the cloud server 101.

[0038] In particular, in the real-time mode of this example, the traffic management department server 102 can realize the cloud storage function. The so-called cloud storage is a new concept extended and developed from the concept of cloud computing. The distributed cloud storage system (hereinafter referred to as the storage system) refers to a storage system that uses cluster applications, grid technology, and distributed storage file systems to bring together a large number of storage devices of various types (storage devices are also called storage nodes) in the network to work together through application software or application interfaces to provide data storage and business access functions to the outside world. At present, the storage method of the storage system is: create a logical volume. When creating a logical volume, a physical storage space is allocated for each logical volume. The physical storage space may be composed of a disk of a storage device or several storage devices. The client stores data on a logical volume, that is, the data is stored on the file system. The file system divides the data into many parts, each of which is an object. The object not only contains data but also contains additional information such as data identification (ID, IDentity). The file system writes each object into the physical storage space of the logical volume, and the file system records the storage location information of each object, so that when the client requests to access the data, the file system can allow the client to access the data according to the storage location information of each object. The process of the storage system allocating physical storage space to a logical volume is as follows: based on the estimated capacity of the objects stored in the logical volume (this estimate often has a large margin relative to the actual capacity of the objects to be stored) and the grouping of independent redundant disk arrays (RAID, Redundant Array of Independent Disk), the physical storage space is divided into stripes in advance. A logical volume can be understood as a stripe, thereby allocating physical storage space to the logical volume.

[0039] The traffic management department server 102 may record vehicle driving information, such as the speed of each vehicle, and the traffic management department server 102 may also record historical traffic accident information on the road. The cloud server 101 may obtain vehicle driving information and historical traffic accident information of vehicles on the road from the traffic management department server 102 according to the protocol.

[0040] The vehicle-mounted terminal 103, the vehicle-mounted terminal 104, the vehicle-mounted terminal 105, and the vehicle-mounted terminal 106 can be devices installed on the vehicle, which can record the vehicle driving information and provide computing and analysis capabilities. For example, a driving recorder, a vehicle-mounted computer, a smart phone, a tablet computer, a laptop computer, a desktop computer, a smart speaker, a smart watch, etc., but not limited to this. The number of vehicle-mounted terminals on each vehicle can be set according to demand. For example, a vehicle can include two terminals, a smart phone and a vehicle-mounted computer. The traffic management department server 102 can collect vehicle driving information of the vehicle in real time through the vehicle-mounted terminal.

[0041] In the implementation of this example, four vehicles on the road corresponding to the vehicle terminals 103, 104, 105, and 106 are shown, wherein the vehicles corresponding to the vehicle terminals 103 and 104 and the vehicles corresponding to the vehicle terminals 105 and 106 are located on both sides of the dividing strip, and the lanes on both sides are opposite lanes; the vehicles corresponding to the vehicle terminals 103 and 104 are located on the same side of the dividing strip, and the lanes on the same side are the same-side same-direction lanes. It can be understood that the number of vehicles can be the number of all vehicles on the road, for example, 2 to 50 vehicles, etc.

[0042] The vehicle-mounted terminal 103 , the vehicle-mounted terminal 104 , the vehicle-mounted terminal 105 , the vehicle-mounted terminal 106 , the cloud server 101 and the traffic management department server 102 may be directly or indirectly connected via wireless communication, and this application does not impose any special restrictions thereon.

[0043] In one implementation of this example, Figure 1 As shown, the cloud server 101 can obtain the vehicle driving information of the first vehicle and the second vehicle on the road from the vehicle terminals on the first vehicle and the second vehicle (for example, any two vehicles corresponding to the vehicle terminals 103, 104, 105, and 106) or the traffic management department server 102; input the vehicle driving information into the driving risk analysis model to obtain the initial risk information of the driving risk caused by the second vehicle to the first vehicle; obtain the type of the dividing strip of the dividing strip on the road, and obtain the lane type of the second vehicle relative to the first vehicle, the lane type indicating the relative position of the lane where the second vehicle is located and the lane where the first vehicle is located on both sides of the dividing strip; obtain the correction information corresponding to the dividing strip type and the lane type, and use the correction information to correct the initial driving risk information to obtain the final driving risk information of the driving risk caused by the second vehicle to the first vehicle. Then, the cloud server 101 can generate vehicle warning information based on the final driving risk information and send it to the first vehicle; use the first vehicle to output the vehicle warning information to warn the first vehicle of driving risks.

[0044] In another implementation of this example, Figure 1As shown, the vehicle terminal on the first vehicle (for example, the vehicle corresponding to the vehicle terminal 103) can obtain the vehicle driving information of the first vehicle on the road; it can also obtain the vehicle driving information of the second vehicle on the road from the vehicle terminal on the second vehicle (for example, any one of the vehicles corresponding to the vehicle terminal 104, the vehicle terminal 105, and the vehicle terminal 106) or the traffic management department server 102; input the vehicle driving information into the driving risk analysis model to obtain the initial risk information of the driving risk caused by the second vehicle to the first vehicle; obtain the type of the dividing strip of the dividing strip on the road, and obtain the lane type of the second vehicle relative to the first vehicle, the lane type indicating the relative position of the lane where the second vehicle is located and the lane where the first vehicle is located on both sides of the dividing strip; obtain the correction information corresponding to the dividing strip type and the lane type, and use the correction information to correct the initial driving risk information to obtain the final driving risk information of the driving risk caused by the second vehicle to the first vehicle. Then, the vehicle terminal on the first vehicle can generate vehicle warning information according to the final driving risk information; use the first vehicle to output the vehicle warning information to warn the first vehicle of the driving risk.

[0045] like Figure 1 As shown in the figure, when two vehicles on the road are driving in lanes in different directions (opposite lanes on both sides of the dividing strip), the driving risk brought by the vehicle to the other vehicle will be reduced due to traffic regulations or the restrictions of the dividing strip between the opposite lanes (such as pedestrian guardrails, flower beds, etc.). Different types of dividing strips may also bring different driving risks to vehicles (some dividing strips can prevent vehicles from crossing into the opposite lane to a certain extent, but may bring risks to vehicles in the same direction, because the rebound of the vehicle after hitting the dividing strip may bring risks to vehicles in the same lane on the same side. Some dividing strips can only serve as a reminder, but cannot block vehicles, and the degree of reducing the risk to vehicles in the opposite lane is limited).

[0046] The above-mentioned road environment has a wide range of impacts on driving risks. However, the relevant technology believes that there is no driving risk between vehicles on both sides of the dividing strip, which is not in line with reality; it believes that the driving risk between vehicles on the same side of the dividing strip is not as high as the driving risk caused by the rebound of the vehicle after hitting the dividing strip, etc.; insufficient consideration of environmental factors when the vehicle is driving on the road leads to low accuracy of vehicle driving risk analysis, which makes the reliability of vehicle driving risk analysis based on artificial intelligence limited. Furthermore, how to accurately assess the driving risk in this scenario is a key issue in the implementation of technologies such as safe assisted driving.

[0047] Figure 2The flowchart of the vehicle driving risk analysis method based on artificial intelligence according to one embodiment of the present application is schematically shown. The execution subject of the vehicle driving risk analysis method based on artificial intelligence can be an electronic device with computing and processing functions, such as Figure 1 The cloud server 101, the traffic management department server 102 or the vehicle terminal 103, the vehicle terminal 104, the vehicle terminal 105, the vehicle terminal 106, etc. The vehicle driving risk analysis method based on artificial intelligence in this example can be applied to various maps, WeChat applets, and vehicle WeChat scenarios to assist in vehicle navigation, etc.

[0048] like Figure 2 As shown, the artificial intelligence-based vehicle driving risk analysis method may include steps S210 to S240.

[0049] Step S210, obtaining vehicle driving information of a first vehicle and a second vehicle on a passable road;

[0050] Step S220, inputting the vehicle driving information into the driving risk analysis model to obtain initial risk information of the driving risk caused by the second vehicle to the first vehicle;

[0051] Step S230, obtaining a dividing strip type of a dividing strip on the road, and obtaining a lane type of the second vehicle relative to the first vehicle, the lane type indicating a relative position of a lane where the second vehicle is located and a lane where the first vehicle is located on both sides of the dividing strip;

[0052] Step S240, obtaining correction information corresponding to the dividing strip type and the lane type, and using the correction information to correct the initial driving risk information, to obtain final driving risk information of the driving risk caused by the second vehicle to the first vehicle.

[0053] The following describes the specific process of each step in the vehicle driving risk analysis based on artificial intelligence.

[0054] In step S210, vehicle driving information of a first vehicle and a second vehicle on the road is obtained.

[0055] In the implementation of this example, the first vehicle and the second vehicle are any two vehicles on the road, and may also be two vehicles whose distance is less than a predetermined threshold (eg, 150 meters, etc.).

[0056] The vehicle driving information may be relevant information about the vehicle driving on the road, for example, the vehicle's mass, speed, acceleration, GPS coordinates, road viscosity, road friction coefficient, and other information.

[0057] The execution subject of this example implementation can be a vehicle-mounted terminal or a server. When the execution subject is a vehicle-mounted terminal, the vehicle-mounted terminal on the vehicle can obtain information such as the vehicle's own mass, speed, acceleration, GPS coordinates, etc.; the vehicle-mounted terminal of the vehicle can also obtain information from a cloud server (for example, Figure 1 The cloud server 101 or traffic management department server 102 shown in the figure) or roadside equipment (for example, roadside radar, roadside perception unit, cloud camera and other equipment) obtains the mass, speed, acceleration, GPS coordinates and other information of other vehicles, and the vehicle terminal of the vehicle can obtain the road viscosity, road friction coefficient, road curvature, visibility and other information from the meteorological department server. In one example, the vehicle terminal of the first vehicle can obtain the vehicle driving information of the vehicle, and obtain the vehicle driving information of the second vehicle from the cloud server, and then further perform driving risk analysis based on artificial intelligence in subsequent steps.

[0058] When the execution subject is a server, the cloud server (e.g. Figure 1 The cloud server 101 or the traffic management department server 102 shown in the figure can obtain the vehicle's mass, speed, acceleration, GPS coordinates and other information from the vehicle terminal. In one example, the cloud server can obtain the vehicle driving information of the first vehicle and the second vehicle on the road, and then further perform driving risk analysis based on artificial intelligence in subsequent steps.

[0059] In step S220, the vehicle driving information is input into the driving risk analysis model to obtain initial risk information of the driving risk caused by the second vehicle to the first vehicle.

[0060] In the implementation of this example, the driving risk analysis model can also take the vehicle driving information sample set as input, and the initial risk label calibrated for each sample in the sample set as the expected output, and train a deep learning model that meets the requirements (for example, the label output accuracy is higher than a predetermined threshold), such as a decision tree model, etc. The initial risk label can be a risk level, for example, level 1 risk to level 5 risk, and the higher the level, the higher the risk degree.

[0061] The driving risk analysis model can also be a risk calculation model, which can calculate the collision probability or potential collision intensity between any two vehicles based on the parameter values ​​of vehicle driving information such as vehicle speed, acceleration, driving direction, road viscosity, road friction coefficient, road curvature, visibility, etc., and then use the initial risk value such as collision probability or potential collision intensity to represent the initial risk information.

[0062] By inputting the vehicle driving information into the driving risk analysis model, initial risk information on the driving risk caused by the second vehicle to the first vehicle can be obtained based on preliminary analysis of artificial intelligence.

[0063] In one embodiment, the vehicle driving information is input into a driving risk analysis model to obtain initial risk information of the driving risk caused by the second vehicle to the first vehicle, including:

[0064] The first collision intensity SPE of the driving risk caused by the second vehicle to the first vehicle is calculated by using the vehicle driving information based on the following first risk calculation model V_bj (Collision intensity is the work done on the vehicle by the interaction force generated by the vehicle during the collision at the moment of collision):

[0065]

[0066] Among them, the first vehicle is a moving vehicle, and the second vehicle is also a moving vehicle; then, the calculated first collision intensity can be directly used as the initial risk information, or the calculated first collision intensity can be divided by a predetermined value to calculate the first collision probability as the initial risk information.

[0067] Where G is a constant; M is the mass of the vehicle, r is the distance between the vehicles, v is the speed of the vehicle, and R is the road surface factor (e.g., road viscosity, humidity, slope, etc.); subscript b represents the first vehicle, and subscript j represents the second vehicle. θ is the angle between the driving directions of the two vehicles (the driving directions of the vehicles can be represented by the angle between the vehicle speed direction and the true north direction); k1 is the first constant, k2 is the second constant, and k3 is the third constant, for example, k1 = 3, k2 = 1, and k3 = the speed of light.

[0068] In one embodiment, the vehicle driving information is input into a driving risk analysis model to obtain initial risk information of the driving risk caused by the second vehicle to the first vehicle, including:

[0069] The second collision intensity SPE of the driving risk caused by the second vehicle to the first vehicle is calculated by using the vehicle driving information based on the following second risk calculation model R_aj (Collision intensity is the work done on the vehicle by the interaction force generated by the vehicle during the collision at the moment of collision):

[0070]

[0071] Among them, the first vehicle is a moving vehicle, and the second vehicle is a stationary vehicle (for example, a stationary vehicle stopped on the road due to lack of fuel, etc.); then, the calculated second collision intensity can be directly used as the initial risk information, or the calculated second collision probability can be calculated by dividing the calculated second collision intensity by a predetermined value as the initial risk information.

[0072] Where G is a constant; M is the mass of the vehicle, r is the distance between the vehicles, V is the speed of the vehicle, and R is the road surface factor (for example, the viscosity, humidity, slope, etc. of the road surface); the subscript a of R, M represents the first vehicle, and the subscript j represents the second vehicle. θ is the angle between the driving directions of the two vehicles (the driving directions of the vehicles can be expressed by the angle between the vehicle speed direction and the north direction); k1 is the first constant, k2 is the second constant, and k3 is the third constant, for example, k1=3, k2=1, k3=the speed of light; D is the road width; LT a It refers to the type of road sign. For example, it can take values ​​1, 2, 3, 4, etc. to identify different types of road signs (the more stress the road sign brings to the driver, the more LT a The larger the value).

[0073] In step S230, the type of the dividing strip on the road is obtained, and the lane type of the second vehicle relative to the first vehicle is obtained, where the lane type indicates the relative position of the lane where the second vehicle is located and the lane where the first vehicle is located on both sides of the dividing strip.

[0074] In the implementation of this example, the dividing strip is a separation strip on the road used to separate lanes of non-same direction. The lanes on both sides of the dividing strip are opposite lanes on the opposite side, that is, the vehicles on the lanes on both sides of the dividing strip are traveling in opposite directions; the lanes on the same side (for example, the lanes on the right side of the dividing strip) are same-side same-direction lanes, that is, the vehicles on the lanes on the same side of the dividing strip are traveling in the same direction.

[0075] The type of the median strip is a type that describes the possibility that the median strip can prevent vehicles from crossing. In this example, the median strip type includes a first type and a second type. The first type indicates a median strip that cannot collide with and block vehicles, that is, a median strip that can only serve as a reminder and cannot collide with vehicles, such as a yellow lane line in the middle of the road; the second type indicates a median strip that can collide with and block vehicles, that is, a median strip that can serve as a reminder and can collide with vehicles to block vehicles to a certain extent, such as a pedestrian guardrail.

[0076] The method for obtaining the type of the dividing strip on the passing road can be to obtain it from the server of the traffic management department or the road maintenance party according to the agreement, or to use the camera on the first vehicle and / or the second vehicle to collect a road image containing the dividing strip on the passing road, and then input the type determination model (pre-trained deep learning model) to obtain the type of the dividing strip on the passing road.

[0077] The lane type of the second vehicle relative to the first vehicle may indicate the relative positions of the lane where the second vehicle is located and the lane where the first vehicle is located on both sides of the dividing strip, and the lane type may include a lane on the opposite side in the opposite direction and a lane on the same side in the same direction.

[0078] The lane type of the second vehicle relative to the first vehicle can be obtained from a cloud server or roadside equipment (such as roadside radar, roadside perception unit, cloud camera, etc.).

[0079] In one embodiment, reference Figure 3 As shown, in step S230: obtaining the type of the dividing strip on the passing road includes:

[0080] Step S310, obtaining a road image including an image of a dividing strip on a passable road;

[0081] Step S320, input the road image into the type determination model to obtain the type of the dividing strip on the passable road. The dividing strip type includes a first type and a second type. The first type indicates a dividing strip that cannot collide and block vehicles, and the second type indicates a dividing strip that can collide and block vehicles.

[0082] The road image including the image of the dividing strip on the passable road may be collected by a front camera of the first vehicle or the second vehicle, or by a cloud camera, etc.

[0083] The type determination model is a pre-trained deep network model that can segment the image into a separation zone image through image segmentation, and then obtain the separation zone type through image matching.

[0084] In one embodiment, reference Figure 4 As shown, in step S230: obtaining the type of the dividing strip on the passing road includes:

[0085] Step S410, when the type of the dividing strip is the second type, obtaining a first occurrence rate of a first accident and a second occurrence rate of a second accident on the road, wherein the first accident is a traffic accident in which a vehicle does not cross the dividing strip after colliding with the dividing strip, and the second accident is a traffic accident in which a vehicle crosses the dividing strip after colliding with the dividing strip;

[0086] Step S420: Determine the subtype of the second type as the separation zone type according to the first occurrence rate and the second occurrence rate.

[0087] The first accident and the second accident are traffic accidents involving the introduction of a dividing strip, wherein the first accident is a traffic accident in which the vehicle did not cross the dividing strip after colliding with the dividing strip, for example, the vehicle did not cross the dividing strip after colliding with the dividing strip, which may cause an accident to other vehicles in the same-side and same-direction lanes due to rebound; the second accident is a traffic accident in which the vehicle crossed the dividing strip after colliding with the dividing strip, for example, the vehicle collided with the dividing strip and crossed the dividing strip, which may cause an accident with other vehicles in the opposite lanes on the opposite side.

[0088] The first occurrence rate and the second occurrence rate can be obtained by respectively calculating the ratio of the number of occurrences of the first accident and the second accident to the total number of traffic accidents within a predetermined period.

[0089] The first occurrence rate and the second occurrence rate correspond to accidents in which the second type of separation strip (separation strip capable of collision blocking vehicles) is introduced, and can respectively reflect the occurrence rates of accidents corresponding to separation strips with different collision blocking effects. Further, according to the occurrence of different collision blocking effects on the road, the subtype of the second type can be determined as the separation strip type, and the determined subtype can reflect the collision blocking effect of the separation strip on vehicles in traffic accidents.

[0090] In one embodiment, reference Figure 5 As shown, step S420: determining the subtype of the second type as the separation zone type according to the first occurrence rate and the second occurrence rate, including:

[0091] Step S510, calculating the first probability that the vehicle cannot cross the dividing strip according to the formula T1=p1 / (p1+p2), where T1 is the first probability, p1 is the first occurrence rate, and p2 is the second occurrence rate;

[0092] Step S520, compare the first probability with the first probability threshold, and determine the subtype of the second type as the dividing strip type, wherein the first probability threshold is used to divide at least two probability ranges, which are probability ranges in which the vehicle cannot cross the dividing strip, and the probability ranges correspond to different subtypes.

[0093] The traffic accidents corresponding to the first occurrence rate p1 and the second occurrence rate p2 are both accidents involving the introduction of a dividing strip, and the first occurrence rate p1 is the accident occurrence rate in which the vehicle does not cross the dividing strip, and the second occurrence rate p2 is the accident occurrence rate in which the vehicle crosses the dividing strip. Furthermore, the first probability that the vehicle cannot cross the dividing strip can be calculated according to p1 / (p1+p2).

[0094] The first probability threshold is a probability threshold set according to experimental analysis, and can be divided into at least two probability ranges, wherein when the first probability threshold has only one threshold, it can be divided into two probability ranges, for example, when the first probability threshold is 50%, it can be divided into two probability ranges of 0% to 50% and 50% to 100%. When the first probability threshold has two thresholds, it can be divided into three probability ranges, for example, when the first probability threshold is 50% and 70%, it can be divided into three probability ranges of 0% to 50%, 50% to 70%, and 70% to 100%.

[0095] This probability range is the probability range that the vehicle cannot cross the dividing strip, and the probability range corresponds to different subtypes (which can reflect the collision blocking effect of the dividing strip on the vehicle). Therefore, by comparing the first probability that the vehicle cannot cross the dividing strip with the first probability threshold, the probability range where the first probability lies can be determined. Then, the subtype of the dividing strip on the road for the current vehicle (the first vehicle or the second vehicle) is determined, that is, the higher the probability range corresponding to the subtype, the higher the probability that the current vehicle cannot cross the dividing strip when driving on the current road, and the more difficult it is to cross the dividing strip.

[0096] In one embodiment, reference Figure 6 As shown, step S420: determining the subtype of the second type as the separation zone type according to the first occurrence rate and the second occurrence rate, including:

[0097] Step S610, obtaining a first average mass of vehicles in a first accident and a first average speed of the vehicles when they hit a dividing strip;

[0098] Step S620, obtaining a second average mass of the vehicles in the second accident and a second average speed of the vehicles when they hit the dividing strip;

[0099] Step S630, calculating the second probability that the vehicle cannot cross the dividing strip according to the formula T2=(m1*v1*p1) / (m1*v1*p1+m2*v2*p2)), where T2 is the second probability, p1 is the first occurrence rate, m1 is the first average mass, v1 is the first average speed, p2 is the second occurrence rate, m2 is the second average mass, and v2 is the second average speed;

[0100] Step S640, compare the second probability with the second probability threshold, and determine the subtype of the second type as the dividing strip type, wherein the second probability threshold is used to divide at least two probability ranges, which are probability ranges in which the vehicle cannot cross the dividing strip, and the probability ranges correspond to different subtypes.

[0101] The traffic accidents corresponding to the first accident and the second accident are both accidents involving the introduction of a dividing strip, and the first occurrence rate p1, the first average mass m1, and the first average speed v1 are respectively the accident occurrence rate, the average mass, and the average speed of the vehicle in the first accident that the vehicle did not cross the dividing strip, and the second occurrence rate p2, the second average mass m2, and the second average speed v2 are respectively the accident occurrence rate, the average mass, and the average speed of the vehicle in the second accident that the vehicle crossed the dividing strip. Figure 5On the basis of the shown embodiment, by further considering the influence of the average mass and average speed of the vehicles in the accident on the collision blocking capacity of the dividing strip, the second probability that the vehicle cannot cross the dividing strip can be further more accurately calculated according to (m1*v1*p1) / (m1*v1*p1+m2*v2*p2)).

[0102] The second probability threshold is a probability threshold set according to experimental analysis, and can be divided into at least two probability ranges, wherein when the second probability threshold has only one threshold, it can be divided into two probability ranges, for example, when the second probability threshold is 60%, it can be divided into two probability ranges of 0% to 60% and 60% to 100%. When the second probability threshold has two thresholds, it can be divided into three probability ranges, for example, when the second probability threshold is 60% and 80%, it can be divided into three probability ranges of 0% to 60%, 60% to 80%, and 80% to 100%.

[0103] This probability range is the probability range that the vehicle cannot cross the dividing strip, and the probability range corresponds to different subtypes (which can reflect the collision blocking effect of the dividing strip on the vehicle). Therefore, by comparing the second probability that the vehicle cannot cross the dividing strip with the second probability threshold, the probability range where the first probability lies can be determined. Then, the subtype of the dividing strip on the road for the current vehicle (the first vehicle or the second vehicle) is determined, that is, the higher the probability range corresponding to the subtype, the higher the probability that the current vehicle cannot cross the dividing strip when driving on the road, and the more difficult it is to cross the dividing strip.

[0104] In step S240, correction information corresponding to the dividing strip type and the lane type is obtained, and the initial driving risk information is corrected using the correction information to obtain final driving risk information of the driving risk caused by the second vehicle to the first vehicle.

[0105] In the implementation of this example, the correction information is information for correcting the initial driving risk information. In one example, when the initial driving risk information is the initial risk level, the correction information may be level correction information such as level downgrade or upgrade information. For example, the correction information is "upgraded by one level", the initial risk level is "level 2", and the corrected final risk level is "level 3". In another example, when the initial driving risk information is the initial risk value, the correction information may be a correction factor, and the initial risk value may be corrected according to the correction formula to obtain the final risk value.

[0106] The correction information corresponding to the separation strip type and lane type can be obtained from a preset correction information mapping table (for example, a preset correction factor mapping table or a level correction information mapping table). The correction information mapping table stores the mapping relationship between the separation strip type and lane type and the correction information found through experimental analysis.

[0107] The dividing strip type and lane type can accurately reflect the impact on the driving risk of the first vehicle and the second vehicle due to the introduction of the dividing strip on the current road. The initial risk information is corrected based on the correction information corresponding to the dividing strip type and lane type, which effectively considers the impact of the dividing strip on the road on the driving risk, effectively improves the accuracy of vehicle driving risk analysis, and ensures the reliability of vehicle driving risk analysis based on artificial intelligence.

[0108] In one embodiment, reference Figure 7 As shown, step S240: obtaining correction information corresponding to the type of the dividing strip and the type of the lane, and using the correction information to correct the initial driving risk information, to obtain the final driving risk information of the driving risk caused by the second vehicle to the first vehicle, including:

[0109] Step S710, searching for correction factors corresponding to both the separation strip type and the lane type from a preset correction factor mapping table;

[0110] Step S720: Correct the initial driving risk value using the correction factor to obtain a final driving risk value of the driving risk caused by the second vehicle to the first vehicle.

[0111] The preset correction factor mapping table stores the mapping relationship between the strip type and lane type and the correction factor found in the experimental analysis. Then, the correction factor corresponding to the strip type and lane type can be found from the preset correction factor mapping table; then, the initial driving risk value is corrected based on the correction formula.

[0112] In one embodiment, the lane type includes a same-side same-direction lane and a different-side opposite-direction lane; the subtype includes a first subtype and a second subtype, and the probability range corresponding to the first subtype is higher than the probability range corresponding to the second subtype; Figure 8 As shown, step S720: using the correction factor to correct the initial driving risk value to obtain the final driving risk value of the driving risk caused by the second vehicle to the first vehicle, including:

[0113] Step S810, when the type of the dividing strip is the first type and the lane type is the same-side same-direction lane, correct the initial driving risk value according to the formula E=E1*(1+p0);

[0114] Step S820, when the type of the dividing strip is the first type and the type of the lane is the opposite reverse lane, the initial driving risk value is corrected according to the formula E=E1*(1-p0);

[0115] Step S830, when the median type is the first subtype and the lane type is the same-side same-direction lane, correct the initial driving risk value according to the formula E=E1+E1*p1 / (p1+p2) / S;

[0116] Step S840, when the median type is the first subtype and the lane type is the opposite lane, the initial driving risk value is corrected according to the formula E=E1*p2 / (p1+p2) / S;

[0117] Step S850, when the median type is the second subtype and the lane type is the same-side same-direction lane, correct the initial driving risk value according to the formula E=E1+E1*p1 / (p1+p2) / J;

[0118] Step S860, when the median type is the second subtype and the lane type is the opposite lane, the initial driving risk value is corrected according to the formula E=E1*p2 / (p1+p2) / J;

[0119] Among them, E is the final driving risk value, E1 is the initial driving risk value, p0 is the first correction factor, S is the second correction factor, J is the third correction factor, and the second correction factor is greater than the third correction factor.

[0120] The subtype may include a first subtype and a second subtype, the probability range corresponding to the first subtype is higher than the probability range corresponding to the second subtype, the first subtype of the dividing strip is, for example, a flower bed with a high wall or a dividing strip made of thicker wire, and the second subtype is a fence made of thin wire. Therefore, it is more difficult for the first vehicle and the second vehicle to cross the dividing strip of the first subtype than the dividing strip of the second subtype.

[0121] There is no dividing strip between vehicles in the same lane on the same side, but there is a risk of a vehicle hitting the dividing strip causing a rebound impact and injury to vehicles in the same lane on the same side. There is a dividing strip between vehicles in the opposite lane on the opposite side, but there is a risk of a vehicle hitting the dividing strip causing a vehicle in the opposite lane on the opposite side to cross the dividing strip and hit and injure.

[0122] When the dividing strip type is the first type (a dividing strip that cannot collide and block vehicles) and the lane type is a same-side and same-direction lane, the driving risk brought to the first vehicle by the second vehicle in the same-side and same-direction lane will increase. Then, the initial driving risk value can be corrected according to the formula E=E1*(1+p0) (p0 can be approximated as the increased traffic accident rate of vehicles in the same-side and same-direction lane due to the introduction of the first type of dividing strip, that is, it can be approximated as the increased risk ratio of vehicles in the same-side and same-direction lane due to the introduction of the first type of dividing strip).

[0123] When the dividing strip type is the first type and the lane type is the opposite lane, the driving risk brought to the first vehicle by the second vehicle in the opposite lane will be reduced, and the initial driving risk value can be corrected according to the formula E=E1*(1-p0) (p0 can be approximated as the traffic accident rate reduced in the opposite lane due to the introduction of the first type of dividing strip, that is, it can be approximated as the risk ratio reduced in the opposite lane due to the introduction of the first type of dividing strip), where p0 is greater than or equal to 0.

[0124] When the type of the dividing strip is the first subtype (a second type dividing strip that can collide and block vehicles, and it is more difficult for a vehicle to cross the first subtype dividing strip after a collision than to cross the second subtype dividing strip), and the lane type is a same-side and same-direction lane, it means that if a vehicle in the same-side and same-direction lane collides with the first subtype dividing strip, it will rebound and hit a vehicle in the same lane with a probability of p1 / (p1+p2); on the other hand, the higher the level of the first subtype dividing strip, the stronger its collision blocking ability, and the greater the degree to which factors affecting driving risks such as vehicle speed are reduced, so 1 / S is used for correction; furthermore, the initial driving risk value can be reliably corrected according to the formula E=E1+E1*p1 / (p1+p2) / S.

[0125] When the dividing strip type is the first subtype and the lane type is the opposite lane, a vehicle will bring risk to vehicles in the opposite lane only if it crosses the dividing strip; when vehicles in the opposite lane hit the dividing strip, they will cross the first subtype dividing strip with a probability of p2 / (p1+p2), and the higher the level of the first subtype dividing strip, the stronger the collision blocking ability, and the greater the degree to which factors affecting driving risk such as vehicle speed are reduced, so 1 / S is used for correction; furthermore, the initial driving risk value can be reliably corrected according to the formula E=E1*p2 / (p1+p2) / S.

[0126] When the dividing strip type is the second subtype and the lane type is the same-side and same-direction lane, it means that if a vehicle in the same-side and same-direction lane collides with the second subtype dividing strip, it will rebound and hit the vehicle in the same-side and same-direction lane with a probability of p1 / (p1+p2); on the other hand, the second subtype dividing strip is lower in level than the first subtype dividing strip, and its collision blocking ability is lower than that of the first subtype dividing strip, so the degree to which factors affecting driving risk such as vehicle speed are reduced is lower than that of the first subtype dividing strip, so 1 / J (S is greater than J) is used for correction; furthermore, the initial driving risk value can be corrected according to the formula E=E1+E1*p1 / (p1+p2) / J.

[0127] When the dividing strip type is the second subtype and the lane type is the opposite lane, a vehicle will only bring risk to the vehicle in the opposite lane if it crosses the dividing strip; when the vehicle in the opposite lane hits the dividing strip, it will cross the second subtype dividing strip with a probability of p2 / (p1+p2). The second subtype dividing strip is lower in level than the first subtype dividing strip, and has a lower collision blocking ability than the first subtype dividing strip. Therefore, the degree to which factors affecting driving risk such as vehicle speed are reduced is lower than that of the first subtype dividing strip, so 1 / J (S is greater than J) is used for correction; furthermore, the initial driving risk value can be reliably corrected according to the formula E=E1*p2 / (p1+p2) / J.

[0128] In one embodiment, it further includes:

[0129] Generate vehicle warning information based on final driving risk information;

[0130] The first vehicle is used to output vehicle warning information to provide a driving risk warning to the first vehicle.

[0131] By generating vehicle warning information according to the final driving risk information and utilizing the first vehicle to output the vehicle warning information, a driving risk warning can be reliably provided to the first vehicle.

[0132] The experiment was repeated 10 times for this embodiment, and the statistical results are shown in the following table. It can be seen that the missed alarm rate and false alarm rate of the risk warning of this embodiment are respectively lower than the missed alarm rate and false alarm rate of the related art.

[0133] Experimental sequence Existing technology false negative rate The underreporting rate of this application False alarm rate of existing technology False alarm rate of this application 1 39% 4% 36% 7% 2 36% 5% 34% 6% 3 37% 5% 34% 4% 4 38% 7% 36% 5% 5 37% 4% 35% 4% 6 39% 7% 35% 5% 7 38% 6% 37% 6% 8 37% 7% 34% 7% 9 39% 6% 36% 6% 10 37% 5% 35% 6%

[0134] Fig. 9 A block diagram of an artificial intelligence-based vehicle driving risk analysis device according to an embodiment of the present application is shown.

[0135] like Fig. 9 As shown, the vehicle driving risk analysis device 900 based on artificial intelligence may include a first acquisition module 910 , a pre-analysis module 920 , a second acquisition module 930 and a correction module 940 .

[0136] The first acquisition module 910 can be used to obtain vehicle driving information of the first vehicle and the second vehicle on the pass road; the pre-analysis module 920 can be used to input the vehicle driving information into a driving risk analysis model to obtain initial risk information of the driving risk caused by the second vehicle to the first vehicle; the second acquisition module 930 can be used to obtain the dividing strip type of the dividing strip on the pass road, and obtain the lane type of the second vehicle relative to the first vehicle, the lane type indicating the relative position of the lane where the second vehicle is located and the lane where the first vehicle is located on both sides of the dividing strip; the correction module 940 can be used to obtain correction information corresponding to the dividing strip type and the lane type, and use the correction information to correct the initial driving risk information to obtain the final driving risk information of the driving risk caused by the second vehicle to the first vehicle.

[0137] In some embodiments of the present application, the second acquisition module is configured to: acquire a road image including an image of a dividing strip on the passable road; input the road image into a type determination model to obtain a dividing strip type of the dividing strip on the passable road, the dividing strip type including a first type and a second type, the first type indicating a dividing strip that cannot collide and block vehicles, and the second type indicating a dividing strip that can collide and block vehicles.

[0138] In some embodiments of the present application, the second acquisition module is configured to: when the dividing strip type is the second type, obtain a first occurrence rate of a first accident and a second occurrence rate of a second accident on the pass road, the first accident being a traffic accident in which a vehicle does not cross the dividing strip after colliding with the dividing strip, and the second accident being a traffic accident in which a vehicle crosses the dividing strip after colliding with the dividing strip; based on the first occurrence rate and the second occurrence rate, determine a subtype of the second type as the dividing strip type.

[0139] In some embodiments of the present application, the second acquisition module is configured to: calculate the first probability that the vehicle cannot cross the dividing strip according to the formula T1=p1 / (p1+p2), wherein T1 is the first probability, p1 is the first occurrence rate, and p2 is the second occurrence rate; compare the first probability with the first probability threshold, and determine the subtype of the second type as the dividing strip type, wherein the first probability threshold is used to divide at least two probability ranges, and the probability ranges are the probability ranges that the vehicle cannot cross the dividing strip, and the probability ranges correspond to different subtypes respectively.

[0140] In some embodiments of the present application, the second acquisition module is configured to: obtain the first average mass of the vehicle in the first accident and the first average speed of the vehicle when it hits the dividing strip; obtain the second average mass of the vehicle in the second accident and the second average speed of the vehicle when it hits the dividing strip; calculate the second probability that the vehicle cannot cross the dividing strip according to the formula T2=(m1*v1*p1) / (m1*v1*p1+m2*v2*p2)), where T2 is the second probability, p1 is the first occurrence rate, m1 is the first average mass, v1 is the first average speed, p2 is the second occurrence rate, m2 is the second average mass, and v2 is the second average speed; compare the second probability with the second probability threshold, and determine the subtype of the second type as the dividing strip type, where the second probability threshold is used to divide at least two probability ranges, the probability ranges are the probability ranges that the vehicle cannot cross the dividing strip, and the probability ranges correspond to different subtypes respectively.

[0141] In some embodiments of the present application, the correction module is configured to: search for a correction factor corresponding to both the separation strip type and the lane type from a preset correction factor mapping table;

[0142] The initial driving risk value is corrected using the correction factor to obtain a final driving risk value of the driving risk caused by the second vehicle to the first vehicle.

[0143] In some embodiments of the present application, the lane type includes a same-side same-direction lane and an opposite-side reverse lane; the subtype includes a first subtype and a second subtype, and the probability range corresponding to the first subtype is higher than the probability range corresponding to the second subtype; the correction module is configured to: when the dividing strip type is the first type and the lane type is the same-side same-direction lane, correct the initial driving risk value according to the formula E=E1*(1+p0); when the dividing strip type is the first type and the lane type is the opposite-side reverse lane, correct the initial driving risk value according to the formula E=E1*(1-p0); when the dividing strip type is the first subtype and the lane type is the same-side same-direction lane, correct the initial driving risk value according to the formula E=E1+E1*p1 / (p1+p2) / S driving risk value; when the dividing strip type is the first subtype and the lane type is the opposite-side reverse lane, the initial driving risk value is corrected according to the formula E=E1*p2 / (p1+p2) / S; when the dividing strip type is the second subtype and the lane type is the same-side same-direction lane, the initial driving risk value is corrected according to the formula E=E1+E1*p1 / (p1+p2) / J; when the dividing strip type is the second subtype and the lane type is the opposite-side reverse lane, the initial driving risk value is corrected according to the formula E=E1*p2 / (p1+p2) / J; wherein E is the final driving risk value, E1 is the initial driving risk value, p0 is the first correction factor, S is the second correction factor, and J is the third correction factor, and the second correction factor is greater than the third correction factor.

[0144] In some embodiments of the present application, the warning module is also configured to: generate vehicle warning information according to the final driving risk information; and use the first vehicle to output the vehicle warning information to provide a driving risk warning for the first vehicle.

[0145] It should be noted that, although several modules or units of the equipment for action execution are mentioned in the above detailed description, this division is not mandatory. In fact, according to the embodiments of the present application, the features and functions of two or more modules or units described above can be embodied in one module or unit. On the contrary, the features and functions of one module or unit described above can be further divided into being embodied by multiple modules or units.

[0146] Fig.10 A block diagram of an electronic device according to an embodiment of the present application is schematically shown.

[0147] It should be noted that Fig.10 The electronic device 1000 shown is only an example and should not bring any limitation to the functions and scope of use of the embodiments of the present application.

[0148] like Fig.10 As shown, the electronic device 500 includes a central processing unit (CPU) 1001, which can perform various appropriate actions and processes according to the program stored in the read-only memory (ROM) 1002 or the program loaded from the storage part 1008 into the random access memory (RAM) 1003. In the RAM 1003, various programs and data required for system operation are also stored. The CPU 1001, the ROM 1002, and the RAM 1003 are connected to each other via a bus 1004. An input / output (I / O) interface 1005 is also connected to the bus 1004.

[0149] The following components are connected to the I / O interface 1005: an input section 1006 including a keyboard, a mouse, etc.; an output section 1007 including a cathode ray tube (CRT), a liquid crystal display (LCD), etc., and a speaker, etc.; a storage section 1008 including a hard disk, etc.; and a communication section 1009 including a network interface card such as a LAN (local area network) card, a modem, etc. The communication section 1009 performs communication processing via a network such as the Internet. A drive 1010 is also connected to the I / O interface 1005 as needed. A removable medium 1011, such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, etc., is installed on the drive 1010 as needed, so that a computer program read therefrom is installed into the storage section 1008 as needed.

[0150] In particular, according to an embodiment of the present application, the process described below with reference to the flowchart can be implemented as a computer software program. For example, an embodiment of the present application includes a computer program product, which includes a computer program carried on a computer-readable medium, and the computer program includes a program code for executing the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from a network through a communication part 1009, and / or installed from a removable medium 1011. When the computer program is executed by a central processing unit (CPU) 1001, various functions defined in the system of the present application are executed.

[0151] It should be noted that the computer-readable medium shown in the present application may be a computer-readable signal medium or a computer-readable storage medium or any combination of the above two. The computer-readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or device, or any combination of the above. More specific examples of computer-readable storage media may include, but are not limited to: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In the present application, a computer-readable storage medium may be any tangible medium containing or storing a program that can be used by or in combination with an instruction execution system, device or device. In the present application, a computer-readable signal medium may include a data signal propagated in a baseband or as part of a carrier wave, which carries a computer-readable program code. This propagated data signal may take a variety of forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the above. Computer-readable signal media may also be any computer-readable medium other than computer-readable storage media, which may send, propagate or transmit a program for use by or in conjunction with an instruction execution system, apparatus or device. The program code contained on the computer-readable medium may be transmitted using any appropriate medium, including but not limited to: wireless, wire, optical cable, RF (radio frequency), etc., or any suitable combination of the above.

[0152] The flow chart and block diagram in the accompanying drawings illustrate the possible architecture, function and operation of the system, method and computer program product according to various embodiments of the present application. In this regard, each box in the flow chart or block diagram can represent a module, a program segment or a part of a code, and the above-mentioned module, program segment or a part of a code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the box can also occur in a different order from the order marked in the accompanying drawings. For example, two boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the block diagram or flow chart, and the combination of the boxes in the block diagram or flow chart can be implemented with a dedicated hardware-based system that performs a specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.

[0153] The units involved in the embodiments described in this application may be implemented by software or hardware, and the units described may also be set in a processor. The names of these units do not, in some cases, constitute limitations on the units themselves.

[0154] As another aspect, the present application also provides a computer-readable medium, which may be included in the electronic device described in the above embodiment; or may exist independently without being assembled into the electronic device. The above computer-readable medium carries one or more programs, and when the above one or more programs are executed by an electronic device, the electronic device implements the method described in the above embodiment.

[0155] It should be noted that, although several modules or units of the equipment for action execution are mentioned in the above detailed description, this division is not mandatory. In fact, according to the embodiments of the present application, the features and functions of two or more modules or units described above can be embodied in one module or unit. On the contrary, the features and functions of one module or unit described above can be further divided into being embodied by multiple modules or units.

[0156] Through the description of the above implementation methods, it is easy for those skilled in the art to understand that the example implementation methods described here can be implemented by software or by combining software with necessary hardware. Therefore, the technical solution according to the implementation methods of the present application can be embodied in the form of a software product, which can be stored in a non-volatile storage medium (which can be a CD-ROM, a USB flash drive, a mobile hard disk, etc.) or on a network, and includes several instructions to enable a computing device (which can be a personal computer, a server, a touch terminal, or a network device, etc.) to execute the method according to the implementation methods of the present application.

[0157] Those skilled in the art will readily appreciate other embodiments of the present application after considering the specification and practicing the embodiments disclosed herein. The present application is intended to cover any variations, uses or adaptations of the present application, which follow the general principles of the present application and include common knowledge or customary technical means in the art that are not disclosed in the present application.

[0158] It should be understood that the present application is not limited to the embodiments that have been described above and shown in the accompanying drawings, but various modifications and changes may be made without departing from the scope thereof.

Claims

1. A vehicle driving risk analysis method based on artificial intelligence, characterized in that: include: Acquiring vehicle driving information of a first vehicle and a second vehicle on a passable road; Inputting the vehicle driving information into a driving risk analysis model to obtain initial driving risk information of the second vehicle causing driving risk to the first vehicle; Obtaining a type of a dividing strip on the passing road, and obtaining a lane type of the second vehicle relative to the first vehicle, wherein the lane type indicates the relative position of a lane where the second vehicle is located and a lane where the first vehicle is located on both sides of the dividing strip; wherein the dividing strip type includes a first type and a second type, wherein the first type indicates a dividing strip that cannot be blocked by a collision, and the second type indicates a dividing strip that can be blocked by a collision; Correction information corresponding to the dividing strip type and the lane type is obtained, and the initial driving risk information is corrected using the correction information to obtain final driving risk information of the driving risk caused by the second vehicle to the first vehicle.

2. The method according to claim 1, characterized in that The obtaining of the type of the dividing strip of the dividing strip on the passing road comprises: Acquire a road image including an image of a dividing strip on the passable road; The road image is input into a type determination model to obtain the type of the dividing strip on the passing road.

3. The method according to claim 2, characterized in that The obtaining of the type of the dividing strip on the passing road further includes: When the type of the dividing strip is the second type, a first occurrence rate of a first accident and a second occurrence rate of a second accident on the traffic road are obtained, wherein the first accident is a traffic accident in which a vehicle does not cross the dividing strip after colliding with the dividing strip, and the second accident is a traffic accident in which a vehicle crosses the dividing strip after colliding with the dividing strip; According to the first occurrence rate and the second occurrence rate, a subtype of the second type is determined as the type of the dividing strip, wherein the subtype of the second type is used to reflect the collision blocking effect of the dividing strip on the vehicle.

4. The method according to claim 3, characterized in that The step of determining the subtype of the second type as the separation zone type according to the first occurrence rate and the second occurrence rate includes: Calculate the first probability that the vehicle cannot cross the dividing strip according to the formula T1=p1 / (p1+p2), where T1 is the first probability, p1 is the first occurrence rate, and p2 is the second occurrence rate; Compare the first probability with the first probability threshold, and determine the subtype of the second type as the dividing strip type, wherein the first probability threshold is used to divide at least two probability ranges, the probability ranges are probability ranges in which the vehicle cannot cross the dividing strip, and the probability ranges correspond to different subtypes respectively.

5. The method according to claim 3, characterized in that: The step of determining the subtype of the second type as the separation zone type according to the first occurrence rate and the second occurrence rate further includes: Obtaining a first average mass of the vehicles in the first accident and a first average speed of the vehicles when they hit the dividing strip; Obtaining a second average mass of the vehicles in the second accident and a second average speed of the vehicles when they hit the dividing strip; Calculate the second probability that the vehicle cannot cross the dividing strip according to the formula T2=(m1*v1*p1) / (m1*v1*p1+m2*v2*p2)), where T2 is the second probability, p1 is the first occurrence rate, m1 is the first average mass, v1 is the first average speed, p2 is the second occurrence rate, m2 is the second average mass, and v2 is the second average speed; Compare the second probability with the second probability threshold, and determine the subtype of the second type as the dividing strip type, wherein the second probability threshold is used to divide at least two probability ranges, the probability ranges being the probability ranges in which the vehicle cannot cross the dividing strip, and the probability ranges respectively correspond to different subtypes.

6. The method according to claim 4 or 5, characterized in that: The acquiring correction information corresponding to the separation strip type and the lane type, and using the correction information to correct the initial driving risk information to obtain final driving risk information of the driving risk caused by the second vehicle to the first vehicle, includes: Searching for correction factors corresponding to both the separation strip type and the lane type from a preset correction factor mapping table; The initial driving risk value is corrected using the correction factor to obtain a final driving risk value of the driving risk caused by the second vehicle to the first vehicle.

7. The method according to claim 6, characterized in that The lane types include a same-side same-direction lane and a different-side opposite-direction lane; the subtypes include a first subtype and a second subtype, and the probability range corresponding to the first subtype is higher than the probability range corresponding to the second subtype; The using the correction factor to correct the initial driving risk value to obtain a final driving risk value of the driving risk caused by the second vehicle to the first vehicle includes: When the type of the dividing strip is the first type and the type of the lane is the same-side same-direction lane, the initial driving risk value is corrected according to the formula E=E1*(1+p0); When the type of the dividing strip is the first type and the type of the lane is the opposite-side reverse lane, the initial driving risk value is corrected according to the formula E=E1*(1-p0); When the type of the dividing strip is the first subtype and the type of the lane is the same-side same-direction lane, the initial driving risk value is corrected according to the formula E=E1+E1*p1 / (p1+p2) / S; When the type of the dividing strip is the first subtype and the type of the lane is the opposite reverse lane, the initial driving risk value is corrected according to the formula E=E1*p2 / (p1+p2) / S; When the type of the dividing strip is the second subtype and the type of the lane is the same-side same-direction lane, the initial driving risk value is corrected according to the formula E=E1+E1*p1 / (p1+p2) / J; When the type of the dividing strip is the second subtype and the type of the lane is the opposite reverse lane, the initial driving risk value is corrected according to the formula E=E1*p2 / (p1+p2) / J; Wherein, E is the final driving risk value, E1 is the initial driving risk value, p0 is the first correction factor, S is the second correction factor, and J is the third correction factor, and the second correction factor is greater than the third correction factor.

8. The method according to claim 1, characterized in that After acquiring correction information corresponding to the separation strip type and the lane type, and using the correction information to correct the initial driving risk information, and obtaining final driving risk information brought by the second vehicle to the first vehicle, the method further includes: generating vehicle warning information according to the final driving risk information; The vehicle warning information is outputted by the first vehicle to provide a driving risk warning to the first vehicle.

9. A vehicle driving risk analysis device based on artificial intelligence, characterized in that: include: A first acquisition module is used to acquire vehicle driving information of a first vehicle and a second vehicle on a passing road; a pre-analysis module, configured to input the vehicle driving information into a driving risk analysis model to obtain initial driving risk information of the second vehicle causing driving risk to the first vehicle; A second acquisition module is used to acquire the type of the dividing strip of the dividing strip on the passing road, and acquire the lane type of the second vehicle relative to the first vehicle, wherein the lane type indicates the relative position of the lane where the second vehicle is located and the lane where the first vehicle is located on both sides of the dividing strip; wherein the dividing strip type includes a first type and a second type, wherein the first type indicates a dividing strip that cannot be blocked by a collision, and the second type indicates a dividing strip that can be blocked by a collision; A correction module is used to obtain correction information corresponding to the separation strip type and the lane type, and use the correction information to correct the initial driving risk information to obtain final driving risk information of the driving risk caused by the second vehicle to the first vehicle.

10. An electronic device, characterized in that: include: a memory storing computer-readable instructions; A processor reads the computer-readable instructions stored in the memory to execute the method according to any one of claims 1 to 8.

11. A computer readable medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the method according to any one of claims 1 to 8 is implemented.

12. A computer program product, characterized in that The computer program product comprises a computer program, which is stored in a computer-readable storage medium. A processor of an electronic device reads and executes the computer program from the computer-readable storage medium, so that the electronic device executes the method according to any one of claims 1 to 8.