Vehicle operation risk quantitative evaluation method and related equipment

Abstract

The invention discloses a vehicle operation risk quantitative evaluation method and related equipment. The method comprises the following steps: acquiring a risk field form extracted from a road environment when a target vehicle is in a motion state; determining a safety range boundary based on the risk field form, and constructing a risk field boundary model; and performing risk quantitative evaluation processing on the risk field boundary model based on a spring model to obtain a vehicle operation risk value. According to the embodiment of the invention, the risk assessment accuracy during vehicle operation can be improved, and the method can be widely applied to the technical field of intelligent traffic.

Description

Technical Field

[0001] This application relates to the field of intelligent transportation technology, and in particular to a method and related equipment for quantitative assessment of vehicle operation risks. Background Technology

[0002] With the continuous increase in car ownership in modern society, road traffic safety has become a focus of public attention, and vehicle collisions are a key cause of frequent traffic accidents. While some technologies utilize risk fields for assessment, practical applications have revealed ambiguities in defining the boundaries of these risk fields, and risk assessments often employ indirect, non-quantitative methods, failing to meet the demands of intelligent driving systems for high-precision, real-time risk perception.

[0003] In summary, the technical problems existing in the relevant technologies need to be improved. Summary of the Invention

[0004] The main objective of this application is to propose a method and related equipment for quantitative assessment of vehicle operation risks, which can improve the accuracy of vehicle operation risk quantification.

[0005] To achieve the above objectives, one aspect of this application proposes a method for quantitatively assessing vehicle operation risks, the method comprising: The risk field morphology of the target vehicle is extracted from the road environment while it is in motion. Based on the risk field morphology, the safety range boundary is determined, and a risk field boundary model is constructed. The risk field boundary model is subjected to risk quantification assessment based on the spring model to obtain the vehicle operation risk value.

[0006] In some embodiments, obtaining the risk field morphology extracted from the road environment when the target vehicle is in motion includes the following steps: The target vehicle performs lane number and geometric feature recognition processing on the road environment to obtain the lane environment; When the lane environment is a single-lane environment, a rectangular risk field shape is constructed with the target vehicle as the center; When the lane environment is a two-lane or multi-lane environment, the risk field shape is obtained by vertically superimposing the longitudinal risk area covering the front and rear directions and the lateral risk area covering the left and right adjacent lanes, and is dynamically adjusted based on the lane-changing behavior of the target vehicle.

[0007] In some embodiments, determining the safety range boundary based on the risk field morphology and constructing a risk field boundary model includes the following steps: Based on the risk field morphology, the kinematic parameters of the target vehicle and adjacent vehicles are extracted and processed to obtain vehicle motion parameters; The vehicle motion parameters are input into a pre-trained critical car-following model for calculation to obtain the first safety boundary; The second safety boundary is calculated based on the geometric features of the target vehicle and adjacent vehicles. The risk field boundary model is constructed based on the first security boundary and the second security boundary.

[0008] In some embodiments, the risk quantification assessment of the risk field boundary model based on the spring model to obtain the vehicle operation risk value includes the following steps: Risk triggering parameters and multidimensional influencing factors are extracted when the target vehicle intrudes into the risk field boundary model due to an obstacle vehicle. Based on the spring model, the risk triggering parameters are calculated to obtain an initial risk value; The initial risk value is corrected based on the multidimensional influencing factors to obtain the vehicle operation risk value.

[0009] In some embodiments, the step of calculating the risk value of the risk triggering parameter based on the spring model to obtain an initial risk value includes the following steps: The intrusion distance of the obstacle vehicle relative to the risk field boundary model is determined based on the risk triggering parameters; The potential collision time between the target vehicle and the obstacle vehicle is calculated based on the intrusion distance. Based on the spring model, the intrusion distance is used as the spring compression amount, and a spatiotemporal integrated risk quantification calculation is performed based on the risk field boundary model and the risk collision time to obtain the initial risk value.

[0010] In some embodiments, the step of performing risk correction processing on the initial risk value based on the multidimensional influencing factors to obtain the vehicle operation risk value includes the following steps: The speed dynamics factor, road environment constraint factor, and driving behavior characteristic factor are extracted from the multidimensional influencing factors. The initial risk value is quantitatively evaluated using the speed dynamic influence factor, the road environment constraint factor, and the driving behavior characteristic factor to obtain the vehicle operation risk value.

[0011] In some embodiments, the method further includes: The risk level is obtained by classifying the vehicle operation risk value based on a preset risk threshold. Based on the risk level, corresponding warning information is output to the driving object or driving system, and an avoidance strategy is predicted based on the warning information through artificial intelligence algorithms.

[0012] To achieve the above objectives, another aspect of this application provides a vehicle operation risk quantification assessment device, the device comprising: The risk field morphology module is used to obtain the risk field morphology extracted from the road environment when the target vehicle is in motion; The risk field boundary module is used to determine the safety range boundary based on the risk field morphology and construct the risk field boundary model. The risk quantification module is used to perform risk quantification assessment on the risk field boundary model based on the spring model to obtain the vehicle operation risk value.

[0013] To achieve the above objectives, another aspect of this application provides an electronic device, which includes a memory and a processor. The memory stores a computer program, and the processor executes the computer program to implement the method described above.

[0014] To achieve the above objectives, another aspect of the embodiments of this application proposes a computer-readable storage medium storing a computer program that, when executed by a processor, implements the methods described above.

[0015] The embodiments of this application include at least the following beneficial effects: This application provides a method and related equipment for quantitatively assessing vehicle operation risks. This solution extracts the risk field morphology from the road environment when the target vehicle is in motion, accurately reflecting the real traffic scenario of the target vehicle. Furthermore, this solution constructs a risk field boundary model by determining the safety range boundary based on the risk field morphology. This allows for the construction of a complete risk field boundary model, providing a foundation for subsequent integration with the spring model. Additionally, this solution performs risk quantification assessment on the risk field boundary model based on the spring model to obtain the vehicle operation risk value. This directly quantifies complex driving risks into a normalized value, improving the accuracy of vehicle operation risk quantification and providing drivers with a more accurate and practical safety distance reference. Attached Figure Description

[0016] Figure 1 This is a schematic diagram of an implementation environment provided in the embodiments of this application; Figure 2 This is a flowchart of a method for quantitatively assessing vehicle operation risks provided in an embodiment of this application; Figure 3 This is a schematic diagram of a spring-risk field theoretical model provided in an embodiment of this application; Figure 4 This is a schematic diagram illustrating the application of a risk field model provided in an embodiment of this application; Figure 5 This is a schematic diagram of the structure of a vehicle operation risk quantification assessment device provided in an embodiment of this application; Figure 6 This is a schematic diagram of the hardware structure of the electronic device provided in the embodiments of this application. Detailed Implementation

[0017] To make the objectives, technical solutions, and advantages of this application clearer, the following detailed description is provided in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of this application and are not intended to limit it. In the following description, when referring to the accompanying drawings, unless otherwise indicated, the same numbers in different drawings represent the same or similar elements. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with those of this application; they are merely examples of apparatuses and methods consistent with some aspects of the embodiments of this application as detailed in the appended claims.

[0018] It is understood that the terms “first,” “second,” etc., used in this application may be used herein to describe various concepts, but unless otherwise stated, these concepts are not limited by these terms. These terms are only used to distinguish one concept from another. For example, without departing from the scope of the embodiments of this application, first information may also be referred to as second information, and similarly, second information may also be referred to as first information. Depending on the context, the words “if,” “when,” or “in response to a determination” as used herein may be interpreted as “when…” or “when…” or “in response to a determination.”

[0019] As used in this application, the terms "at least one", "multiple", "each", "any", etc., "at least one" includes one, two or more, "multiple" includes two or more, "each" refers to each of the corresponding multiples, and "any" refers to any one of the multiples.

[0020] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application belongs. The terminology used herein is for the purpose of describing embodiments of this application only and is not intended to limit this application.

[0021] Before providing a detailed description of the embodiments of this application, some of the nouns and terms involved in the embodiments of this application will be explained first. The nouns and terms involved in the embodiments of this application are subject to the following interpretations.

[0022] 1) The risk field is used to characterize the impact of human-vehicle-road elements on driving risk in the vehicle driving environment. By using field theory methods to reveal the properties of the driving safety field under human-vehicle-road interaction and predict the dynamic change trend of the driving safety field, it can be used for state assessment of driving risk in complex environments, driving safety decision design, vehicle driving safety control, and autonomous vehicle path planning, laying a theoretical foundation for driving safety assistance algorithm design and intelligent vehicle path planning.

[0023] With the continuous increase in car ownership in modern society, road traffic safety has become a focus of public attention, and vehicle collisions are a key cause of frequent traffic accidents. Vehicle collisions not only cause personal injury and property damage, but also have many negative impacts on social and economic development.

[0024] Among related technologies, there are methods for safety assessment using risk fields. However, there is ambiguity in the definition of risk field boundaries, and most of them use indirect and non-quantitative methods to assess risks, which is difficult to meet the needs of intelligent driving systems for high-precision and real-time risk perception.

[0025] For example, relevant theories lack a clear definition of the specific geometry and safety boundaries of the risk field for moving vehicles. Although there have been attempts to optimize using elliptical structures, their minor axis cannot cover the full width of the lane, resulting in a delayed response to lateral intrusion risks and blurred boundaries. Furthermore, relevant models primarily rely on distance from lane lines to quantify lateral risk, failing to fully incorporate the dynamic interactions between adjacent lanes and resulting in insufficient assessment of cross-lane conflicts. More importantly, the degree of risk is generally judged indirectly through the "force" of the risk field, rather than by directly and accurately quantifying the risk value, leading to ambiguous assessments and making it difficult to meet high-precision requirements.

[0026] In view of this, this application provides a method and related equipment for quantitative assessment of vehicle operation risks. This scheme starts from spatial structure optimization and risk quantification mechanism. It can construct a dynamic risk field boundary model based on lane geometry features and vehicle dynamic interaction characteristics. By proposing a spatial structure basis for the risk range of moving vehicles, it can achieve dynamic risk coverage of the entire lane width and real-time response to lateral intrusion risks, and clarify the risk field morphology and safety boundary. Furthermore, by introducing a spring model to characterize the attraction-repulsion coupling relationship between vehicles in the risk field, a risk assessment framework integrating risk field theory and spring model is established. It abandons indirect "force" representation and directly establishes a risk value calculation model based on spatiotemporal parameters, providing a new analytical perspective for autonomous driving systems and drivers to avoid risks.

[0027] This application provides a method for quantitatively assessing vehicle operation risks, relating to the field of intelligent transportation technology. This method can be applied to a terminal, a server, or software running on either a terminal or a server. In some embodiments, the terminal can be a smartphone, tablet, laptop, desktop computer, smart speaker, smartwatch, or in-vehicle terminal, but is not limited to these. The server can be configured as an independent physical server, a server cluster or distributed system composed of multiple physical servers, or a cloud server providing basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communication, middleware services, domain name services, security services, CDN, and big data and artificial intelligence platforms. The server can also be a node server in a blockchain network. The software can be an application implementing a method for quantitatively assessing vehicle operation risks, but is not limited to the above forms.

[0028] This application can be used in a wide variety of general-purpose or special-purpose computer system environments or configurations. Examples include: personal computers, server computers, handheld or portable devices, tablet devices, multiprocessor systems, microprocessor-based systems, set-top boxes, programmable consumer electronics devices, network PCs, minicomputers, mainframe computers, and distributed computing environments including any of the above systems or devices. This application can be described in the general context of computer-executable instructions executed by a computer, such as program modules. Generally, program modules include routines, programs, objects, components, data structures, etc., that perform specific tasks or implement specific abstract data types. This application can also be practiced in distributed computing environments where tasks are performed by remote processing devices connected via a communication network. In distributed computing environments, program modules can reside in local and remote computer storage media, including storage devices.

[0029] It should be noted that in all specific embodiments of this application, when processing data related to user identity or characteristics, such as user information, user behavior data, user historical data, and user location information, user permission or consent is obtained first. Furthermore, the collection, use, and processing of this data comply with relevant laws, regulations, and standards. In addition, when embodiments of this application require access to sensitive personal information of users, separate permission or consent from the user is obtained through pop-ups or redirection to confirmation pages. Only after obtaining the user's separate permission or consent is the necessary user-related data required for the proper functioning of these embodiments acquired.

[0030] Figure 1This is a schematic diagram illustrating the implementation environment of a method provided in an embodiment of this application. (Refer to...) Figure 1 The main hardware and software components of this implementation environment include a terminal 101 and a server 102, which are communicatively connected. The method can be executed based on the interaction between the terminal 101 and the server 102. Furthermore, the terminal 101 and the server 102 can be nodes in a blockchain; this embodiment does not specifically limit this.

[0031] Figure 2 This is an optional flowchart of a vehicle operation risk quantification assessment method provided in this application embodiment. Figure 2 The method may include, but is not limited to, steps S201 to S203.

[0032] Step S201: Obtain the risk field morphology extracted from the road environment when the target vehicle is in motion; Step S202: Determine the safety range boundary based on the risk field morphology, and construct the risk field boundary model; Step S203: Based on the spring model, perform risk quantification assessment on the risk field boundary model to obtain the vehicle operation risk value.

[0033] Steps S201 to S203 of the embodiments of this application are used to obtain the risk field morphology of the target vehicle in motion from the road environment. This can depict the specific morphology of the risk field of the vehicle in single-lane, double-lane and multi-lane road environments. Then, the risk field safety boundary is further calculated based on the risk field morphology. Finally, the vehicle operation risk is assessed by combining the spring model and the driving risk field theory to obtain the quantified vehicle operation risk value.

[0034] In step S201 of some embodiments, obtaining the risk field morphology extracted from the road environment when the target vehicle is in motion includes the following steps: The target vehicle performs lane number and geometric feature recognition processing on the road environment to obtain the lane environment; When the lane environment is a single-lane environment, a rectangular risk field shape is constructed with the target vehicle as the center; When the lane environment is a two-lane or multi-lane environment, the risk field shape is obtained by vertically superimposing the longitudinal risk area covering the front and rear directions and the lateral risk area covering the left and right adjacent lanes, and is dynamically adjusted based on the lane-changing behavior of the target vehicle.

[0035] In this embodiment, raw data can be collected using onboard sensors in the target vehicle, such as cameras and lidar. This data is then processed through multiple stages to obtain structured lane environment information. Based on the number of lanes and geometric features of the road where the vehicle is located, a dynamic risk field covering the full width of the target vehicle's driving lane is constructed. Specifically, this embodiment can initially identify lane lines and boundaries using image segmentation or point cloud clustering techniques. Then, based on sequence frame tracking and spatial geometric model fitting, the identification results are converted into precise lane geometric parameters. Simultaneously, through lateral counting and topological relationship analysis of continuous detection results, the number of lanes on the current road and their connectivity are determined, thereby identifying the lane environment. This lane environment includes single-lane, two-lane, or multi-lane environments.

[0036] In a single-lane scenario, the risk primarily originates from vehicles ahead and behind, forming a rectangular risk area that matches the lane geometry. The width of this area is the same as the lane width, and its longitudinal span is dynamically calculated using real-time speed and time data of the target vehicle and its neighboring vehicles. In a two-lane scenario, the risk factors are more complex because they include vehicles from adjacent lanes in addition to forward and backward traffic. The target vehicle primarily experiences risk exposure from adjacent lanes on one side, while the opposite boundary is physically constrained by roadside infrastructure such as curbs or median strips. The definition of the forward and backward risk areas is identical to that under single-lane conditions. The lateral risk area is also rectangular, with its longitudinal length calculated based on the distance between the road edge or median strip and vehicles in adjacent lanes, while its lateral width is identical to the length of the target vehicle. The target vehicle is located at the geometric center where the forward and backward risk areas and the lateral risk area intersect perpendicularly. When a vehicle is traveling in the right lane and is near physical infrastructure such as curbs, guardrails, or median strips, the risk area distribution connecting the endpoints of the rectangle exhibits a linear boundary. In the left-hand lane scenario, physical infrastructure forms the red line boundary, and traffic markings must use a combination of red and yellow markings. In multi-lane environments, the center lane positioning redefines lateral zones while maintaining the definition of the front and rear risk zones. These lateral zones are defined by rectangular boundaries, extending from the rightmost edge of the vehicle immediately to the left to the leftmost edge of the vehicle immediately to the right, with a width equal to the length of the target vehicle. This configuration explicitly considers parallel driving scenarios where multiple vehicles simultaneously occupy adjacent lanes. Furthermore, the driving system can also handle lane-changing maneuvers, such as merging into the rightmost lane, in which case the risk zone is dynamically reconstructed according to the vehicle's position.

[0037] One of the above technical solutions has the following advantages or beneficial effects: By identifying the road environment, the embodiments of this application can clarify the spatial form of the risk field, providing a basis for subsequent risk quantification assessment.

[0038] In some embodiments, determining the safety range boundary based on the risk field morphology and constructing a risk field boundary model includes the following steps: Based on the risk field morphology, the kinematic parameters of the target vehicle and adjacent vehicles are extracted and processed to obtain vehicle motion parameters; The vehicle motion parameters are input into a pre-trained critical car-following model for calculation to obtain the first safety boundary; The second safety boundary is calculated based on the geometric features of the target vehicle and adjacent vehicles. The risk field boundary model is constructed based on the first security boundary and the second security boundary.

[0039] In this embodiment, the kinematic parameters of the target vehicle and adjacent vehicles can be extracted based on the risk field morphology to obtain vehicle motion parameters, including the vehicle's real-time speed, maximum braking deceleration, and driver reaction time. These vehicle motion parameters are then input into a pre-trained critical car-following model for calculation. This critical car-following model can be constructed using a neural network model. The training process can employ a critical headway, incorporating the braking process of the preceding vehicle into the car-following safety distance modeling for more common non-sudden braking scenarios. Calculations based on the critical car-following model yield a first safety boundary. Specifically, when the target vehicle (m) follows the preceding vehicle (q), and the speeds of the two vehicles are respectively... and When car q suddenly brakes to a complete stop, car m, noticing this, immediately brakes. During this process, car m's reaction time encompasses both the driver's reaction time and the time of linear deceleration increase. Let... Let m be the distance between car m and car q when m begins braking. Let q be the distance traveled from the moment it begins braking until it comes to a complete stop. Let be the distance traveled by car m from the start of braking to a complete stop. Without loss of generality, assume that car m and car q have the same maximum braking deceleration. and The calculation expression is as follows: ; ; To ensure that the vehicles do not collide, the distance between vehicle m and vehicle q when vehicle m comes to a complete stop should be greater than 0, that is, the following must be satisfied: ; The minimum safe distance The calculation expression for the first safety boundary is as follows: ; When the speed of the vehicle in front reaches or exceeds that of the target vehicle, the distance between the two vehicles gradually increases over time. In this situation, the safe distance to the target vehicle mainly depends on its own performance characteristics, specifically the total distance from the perception of danger to the completion of braking and stopping. Its calculation logic is similar to... The computational logic remains consistent.

[0040] This application also calculates the second safety boundary based on the geometric features of the target vehicle and adjacent vehicles, and the vehicle width and lane width of the target vehicle and adjacent lane vehicles. The embodiments of this application further explore the calculation of lateral distances, which are closely related to the vehicle's lateral safety. When a vehicle is driving in the center of the lane, the driver's line of sight is more focused, which not only conforms to driving habits but also facilitates observation of road conditions and the dynamics of other vehicles. This avoids the risk of collisions caused by excessively close proximity and ensures that the driver has sufficient space to implement evasive maneuvers or other safety measures in emergency situations, thereby making more accurate driving decisions. Taking a three-lane road as an example, suppose vehicles A, B, and C are driving in their respective lanes. The lane widths from left to right are... , , The widths of vehicles in the corresponding lanes are respectively , , For vehicle B in the middle lane, the calculation expression for its left and right safety distances, i.e., the second safety boundary, is as follows: ; ; One of the above technical solutions has the following advantages or beneficial effects: The embodiments of this application construct a clear risk field spatial form and safety range boundary based on lane geometry and vehicle interaction dynamics, which can clearly define the risk field spatial form of the target vehicle.

[0041] In some embodiments, the risk quantification assessment of the risk field boundary model based on the spring model to obtain the vehicle operation risk value includes the following steps: Risk triggering parameters and multidimensional influencing factors are extracted when the target vehicle intrudes into the risk field boundary model due to an obstacle vehicle. Based on the spring model, the risk triggering parameters are calculated to obtain an initial risk value; The initial risk value is corrected based on the multidimensional influencing factors to obtain the vehicle operation risk value.

[0042] In this embodiment, risk triggering parameters refer to the parameters obtained when an obstacle vehicle intrudes into the risk field boundary model, such as the speed of the obstacle vehicle, the speed of the target vehicle, and the distance between vehicles. Multidimensional influencing factors refer to factors affecting vehicle risk assessment, which may include the vehicle's equivalent mass, speed, road environment, and driver status.

[0043] Specifically, this application's embodiments simulate the interaction forces between vehicles by referencing the elastic deformation characteristics of a spring model. Four virtual springs in the four directions (front, rear, left, and right) are used to represent the vehicle's relative position and dynamic relationship with obstacles or other vehicles. Please refer to [link to relevant documentation]. Figure 3 Initial safe distance Defined as the natural length of the spring, corresponding to the safety range boundary; relative velocity. Mapped to spring constant Change in vehicle distance Δ Corresponding spring deformation The elastic force generated by spring compression This is quantified as a risk intensity indicator. As the two vehicles gradually approach each other, the spring continues to compress, and the relative speed... With deformation Δ A positive correlation is shown, resulting in elasticity The risk value increases significantly, thus effectively characterizing the cumulative effect of collision risk as the distance between vehicles decreases.

[0044] Within the framework of risk field theory, the environment surrounding a vehicle is abstracted as a "field," generating a gradient risk field in the surrounding space. The vehicle experiences a force within this risk field, the magnitude of which has a non-linear relationship with the distance from the field source. This force can be directly quantified as the intensity of the risk experienced by the vehicle, thus reflecting the non-linear cumulative effect of risk as distance decreases. Notably, this logic is highly consistent with the mapping relationship between risk and distance in the spring model: in the spring model, risk is analogous to an elastic force F, the magnitude of which is directly related to the change in vehicle distance L through Hooke's law. Both models reveal a positive correlation and non-linear growth characteristic between risk and distance, and both can characterize the dynamic accumulation process of risk. This logical consistency indicates the feasibility of theoretically integrating risk field theory and the spring model: the former provides global spatial distribution characteristics, while the latter supplements local dynamic response mechanisms; combining the two can construct a unified risk representation framework that combines spatial scalability and dynamic sensitivity.

[0045] In some embodiments, the step of calculating the risk value of the risk triggering parameter based on the spring model to obtain an initial risk value includes the following steps: The intrusion distance of the obstacle vehicle relative to the risk field boundary model is determined based on the risk triggering parameters; The potential collision time between the target vehicle and the obstacle vehicle is calculated based on the intrusion distance. Based on the spring model, the intrusion distance is used as the spring compression amount, and a spatiotemporal integrated risk quantification calculation is performed based on the risk field boundary model and the risk collision time to obtain the initial risk value.

[0046] In this embodiment, the intrusion distance of the obstacle vehicle relative to the risk field boundary model can be calculated based on the risk triggering parameters. Specifically, this embodiment applies a spring model to the field of vehicle risk assessment, using the ratio of spring deformation to spring original length to assess the risk, as expressed below: ; When the distance between vehicles is less than the safe distance (original spring length) When the spring is compressed, it undergoes a "compression," but this "compression" is not an actual physical deformation; rather, it refers to an increase in the risk level. The compression deformation of the spring reflects the proximity of the vehicles; the closer the relative distance between the two vehicles, the higher the risk level. The larger the value, the higher the corresponding risk value. The larger the risk, the greater the risk. This application also introduces Time-To-Collision (TTC) as a key indicator for measuring the time urgency of a risk. TTC reflects the speed of risk accumulation. This application combines it with risk assessment to construct a time-dimensional risk parameter: ; This application embodiment integrates risk parameters from both spatial and temporal dimensions to construct a preliminary risk quantification model, thereby calculating an initial risk value. The expression for this risk quantification model is shown below: ; This model can directly quantify complex driving risks into a normalized value between 0 and 100, intuitively reflecting the current risk level.

[0047] In some embodiments, the step of performing risk correction processing on the initial risk value based on the multidimensional influencing factors to obtain the vehicle operation risk value includes the following steps: The speed dynamics factor, road environment constraint factor, and driving behavior characteristic factor are extracted from the multidimensional influencing factors. The initial risk value is quantitatively evaluated using the speed dynamic influence factor, the road environment constraint factor, and the driving behavior characteristic factor to obtain the vehicle operation risk value.

[0048] In this embodiment of the application, multi-dimensional optimization is performed, taking into account the inherent attributes of the vehicle (equivalent mass M) and the dynamic influence of speed ( Road environment constraints ) and driver behavior characteristics ( The risk assessment model is integrated into the initial risk assessment model, and the risk field strength is modulated by multiple factors to form the final risk assessment model. The expression of the risk assessment model is as follows: ; Finally, the quantified vehicle operation risk value can be calculated using this model. This embodiment integrates multiple influencing factors such as vehicle equivalent mass, speed, road environment, and driver state, ultimately enabling direct and accurate quantification of driving risk into a normalized value of 0-100, and allowing for dynamic definition of the vehicle's safety boundaries.

[0049] In some embodiments, the method further includes: The risk level is obtained by classifying the vehicle operation risk value based on a preset risk threshold. Based on the risk level, corresponding warning information is output to the driving object or driving system, and an avoidance strategy is predicted based on the warning information through artificial intelligence algorithms.

[0050] In this embodiment, the calculated comprehensive risk value (R) is compared with preset risk thresholds (e.g., 50 and 85), and the current risk state is divided into at least three levels: low risk, medium risk, and high risk. Corresponding warning information is then output to the driver or the autonomous driving system. It is conceivable that this embodiment can also utilize machine learning technology to learn the driver's driving habits and vehicle performance, and to personalize the safety boundary (L) or risk threshold for the driver.

[0051] Specifically, the system monitors the vehicle's driving status, road conditions, and the movement of surrounding vehicles in real time. Using advanced algorithms or artificial intelligence, it predicts potential dangerous paths or collision points and dynamically adjusts the safety range boundaries accordingly. The system evaluates different avoidance strategies and, combined with real-time data, provides the driver with optimal avoidance paths or action suggestions. If the driver fails to respond in time or take appropriate measures, the system has the ability to automatically intervene, automatically initiating emergency braking or other safety measures to minimize potential accident risks. The system provides the driver with real-time information and decision support results about emergency situations through a user interface, such as through dashboard displays, audio prompts, or visual displays, so that the driver can quickly make the correct reactions and decisions.

[0052] The embodiments of this application can also utilize vehicle communication, sensor and other technologies to achieve collaborative perception and information sharing with other vehicles, so as to improve the accuracy and real-time performance of safety range boundary determination, thereby further ensuring driving safety.

[0053] The solutions of this application embodiment will be described in detail and explained below with reference to specific application examples: The embodiments of this application can be applied to the field of intelligent transportation technology, mainly involving traffic safety, especially application scenarios concerning the definition of vehicle safety boundaries and risk assessment. Please refer to... Figure 4 Taking a five-lane road as an example, the following scenario is modeled: Target vehicle A is traveling in the middle lane at a speed of 105 km / h, with vehicle D (speed 120 km / h) in front and vehicle E (speed 115 km / h) behind. The lane width is 3.75 meters. Vehicles B and C are in the lanes to A's left and right, respectively. Based on vehicle specifications, vehicle A's dimensions are 5090 × 1879 mm, vehicle B's are 5050 × 1886 mm, and vehicle C's are 4997 × 1963 mm. When vehicles A, B, and C are all traveling on the center line of their respective lanes, the safe distances to vehicle A can be calculated. The driver's reaction time is related to the driver's characteristics and vehicle performance; empirical values ​​are used. The maximum braking deceleration of a vehicle is generally taken as a value. Given the differences in power performance between different vehicle models, it is difficult to determine the specific maximum braking deceleration for each vehicle; therefore, an empirical value is used. Based on the preceding text, the front and rear safe distances of vehicle A can be calculated. Then, by combining this with the final comprehensive risk assessment model, the quantified risk value can be calculated.

[0054] Specifically, this application's embodiments construct a clear risk field spatial form and safety range boundary based on lane geometry and vehicle interaction dynamics, thus clearly defining the risk field spatial form. Secondly, by introducing a physical spring model, the safety boundary is considered as the original length of the spring, and the vehicle intrusion distance is analogized to the spring's compression deformation. Combined with the Time-to-Collision (TTC) index, a spatiotemporal integrated risk quantification assessment framework is constructed. This framework further integrates multi-dimensional influencing factors such as vehicle equivalent mass, speed, road environment, and driver state, ultimately enabling direct and accurate quantification of driving risk into a normalized value of 0-100. This application's embodiments not only achieve dynamic definition of the safety boundary but also provide real-time and accurate risk level assessment, offering intuitive risk warnings for drivers and autonomous driving systems, effectively reducing the probability of collision accidents, and demonstrating significant technological innovation and practical value.

[0055] Please see Figure 5 This application also provides a vehicle operation risk quantification assessment device, which can implement the above-mentioned vehicle operation risk quantification assessment method. The device includes: The risk field morphology module 501 is used to obtain the risk field morphology extracted from the road environment when the target vehicle is in motion. Risk field boundary module 502 is used to determine the safety range boundary based on the risk field morphology and construct a risk field boundary model. The risk quantification module 503 is used to perform risk quantification assessment on the risk field boundary model based on the spring model to obtain the vehicle operation risk value.

[0056] It is understood that the content of the above method embodiments is applicable to the present device embodiments. The specific functions implemented by the present device embodiments are the same as those of the above method embodiments, and the beneficial effects achieved are also the same as those achieved by the above method embodiments.

[0057] This application also provides an electronic device, which includes a memory and a processor. The memory stores a computer program, and the processor executes the computer program to implement the above-described method. This electronic device can be any smart terminal, including tablet computers, in-vehicle computers, etc.

[0058] It is understood that the content of the above method embodiments is applicable to this device embodiment. The specific functions implemented by this device embodiment are the same as those of the above method embodiments, and the beneficial effects achieved are also the same as those achieved by the above method embodiments.

[0059] Please see Figure 6 , Figure 6 The hardware structure of an electronic device according to another embodiment is illustrated. The electronic device includes: The processor 601 can be implemented using a general-purpose CPU (Central Processing Unit), microprocessor, application-specific integrated circuit (ASIC), or one or more integrated circuits, and is used to execute relevant programs to implement the technical solutions provided in the embodiments of this application. The memory 602 can be implemented as a read-only memory (ROM), a static storage device, a dynamic storage device, or a random access memory (RAM). The memory 602 can store the operating system and other applications. When the technical solutions provided in the embodiments of this specification are implemented through software or firmware, the relevant program code is stored in the memory 602 and is called and executed by the processor 601. The input / output interface 603 is used to implement information input and output; The communication interface 604 is used to enable communication and interaction between this device and other devices. Communication can be achieved through wired means (such as USB, network cable, etc.) or wireless means (such as mobile network, WIFI, Bluetooth, etc.). Bus 605 transmits information between various components of the device (e.g., processor 601, memory 602, input / output interface 603, and communication interface 604); The processor 601, memory 602, input / output interface 603, and communication interface 604 are connected to each other within the device via bus 605.

[0060] This application also provides a computer-readable storage medium storing a computer program that, when executed by a processor, implements the above-described method.

[0061] It is understood that the content of the above method embodiments is applicable to this storage medium embodiment. The specific functions implemented in this storage medium embodiment are the same as those in the above method embodiments, and the beneficial effects achieved are also the same as those achieved in the above method embodiments.

[0062] Memory, as a non-transitory computer-readable storage medium, can be used to store non-transitory software programs and non-transitory computer-executable programs. Furthermore, memory may include high-speed random access memory, and may also include non-transitory memory, such as at least one disk storage device, flash memory device, or other non-transitory solid-state storage device. In some embodiments, memory may optionally include memory remotely located relative to the processor, and these remote memories can be connected to the processor via a network. Examples of such networks include, but are not limited to, the Internet, intranets, local area networks, mobile communication networks, and combinations thereof.

[0063] The embodiments described in this application are for the purpose of more clearly illustrating the technical solutions of the embodiments of this application, and do not constitute a limitation on the technical solutions provided by the embodiments of this application. As those skilled in the art will know, with the evolution of technology and the emergence of new application scenarios, the technical solutions provided by the embodiments of this application are also applicable to similar technical problems.

[0064] Those skilled in the art will understand that the technical solutions shown in the figures do not constitute a limitation on the embodiments of this application, and may include more or fewer steps than shown, or combine certain steps, or different steps.

[0065] The device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separate; that is, they may be located in one place or distributed across multiple network units. Some or all of the modules can be selected to achieve the purpose of this embodiment according to actual needs.

[0066] Those skilled in the art will understand that all or some of the steps in the methods disclosed above, as well as the functional modules / units in the systems and devices, can be implemented as software, firmware, hardware, or suitable combinations thereof.

[0067] The terms “first,” “second,” “third,” “fourth,” etc. (if present) in the specification and accompanying drawings of this application are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of this application described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms “comprising” and “having,” and any variations thereof, are intended to cover non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0068] It should be understood that in this application, "at least one (item)" means one or more, and "more than" means two or more. "And / or" is used to describe the relationship between related objects, indicating that three relationships can exist. For example, "A and / or B" can represent three cases: only A exists, only B exists, and both A and B exist simultaneously, where A and B can be singular or plural. The character " / " generally indicates that the preceding and following related objects are in an "or" relationship. "At least one (item) of the following" or similar expressions refer to any combination of these items, including any combination of single or plural items. For example, at least one (item) of a, b, or c can represent: a, b, c, "a and b", "a and c", "b and c", or "a and b and c", where a, b, and c can be single or multiple.

[0069] In the several embodiments provided in this application, it should be understood that the disclosed apparatus and methods can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative; for instance, the division of the units described above is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be through some interfaces; the indirect coupling or communication connection between apparatuses or units may be electrical, mechanical, or other forms.

[0070] The units described above as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0071] Furthermore, the functional units in the various embodiments of this application can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit.

[0072] If the integrated unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes multiple instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods of the various embodiments of this application. The aforementioned storage medium includes various media capable of storing programs, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0073] The preferred embodiments of the present application have been described above with reference to the accompanying drawings, but this does not limit the scope of the claims of the present application. Any modifications, equivalent substitutions, and improvements made by those skilled in the art without departing from the scope and substance of the embodiments of the present application shall be within the scope of the claims of the present application.

Claims

1. A method for quantitatively assessing vehicle operation risks, characterized in that, The method includes the following steps: The risk field morphology is extracted from the road environment when the target vehicle is in motion. Based on the risk field morphology, the safety range boundary is determined, and a risk field boundary model is constructed. The risk field boundary model is subjected to risk quantification assessment based on the spring model to obtain the vehicle operation risk value.

2. The method according to claim 1, characterized in that, The process of extracting the risk field morphology from the road environment when the target vehicle is in motion includes the following steps: The target vehicle performs lane number and geometric feature recognition processing on the road environment to obtain the lane environment; When the lane environment is a single-lane environment, a rectangular risk field shape is constructed with the target vehicle as the center; When the lane environment is a two-lane or multi-lane environment, the risk field shape is obtained by vertically superimposing the longitudinal risk area covering the front and rear directions and the lateral risk area covering the left and right adjacent lanes, and is dynamically adjusted based on the lane-changing behavior of the target vehicle.

3. The method according to claim 1, characterized in that, The process of determining the safety range boundary based on the risk field morphology and constructing the risk field boundary model includes the following steps: Based on the risk field morphology, the kinematic parameters of the target vehicle and adjacent vehicles are extracted and processed to obtain vehicle motion parameters; The vehicle motion parameters are input into a pre-trained critical car-following model for calculation to obtain the first safety boundary; The second safety boundary is calculated based on the geometric features of the target vehicle and adjacent vehicles. The risk field boundary model is constructed based on the first security boundary and the second security boundary.

4. The method according to claim 1, characterized in that, The process of performing risk quantification assessment on the risk field boundary model based on the spring model to obtain the vehicle operation risk value includes the following steps: Risk triggering parameters and multidimensional influencing factors are extracted when the target vehicle intrudes into the risk field boundary model due to an obstacle vehicle. Based on the spring model, the risk triggering parameters are calculated to obtain an initial risk value; The initial risk value is corrected based on the multidimensional influencing factors to obtain the vehicle operation risk value.

5. The method according to claim 4, characterized in that, The process of calculating the risk value of the risk triggering parameter based on the spring model to obtain the initial risk value includes the following steps: The intrusion distance of the obstacle vehicle relative to the risk field boundary model is determined based on the risk triggering parameters; The potential collision time between the target vehicle and the obstacle vehicle is calculated based on the intrusion distance. Based on the spring model, the intrusion distance is used as the spring compression amount, and a spatiotemporal integrated risk quantification calculation is performed based on the risk field boundary model and the risk collision time to obtain the initial risk value.

6. The method according to claim 4, characterized in that, The process of performing risk correction on the initial risk value based on the multidimensional influencing factors to obtain the vehicle operation risk value includes the following steps: The speed dynamics factor, road environment constraint factor, and driving behavior characteristic factor are extracted from the multidimensional influencing factors. The initial risk value is quantitatively evaluated using the speed dynamic influence factor, the road environment constraint factor, and the driving behavior characteristic factor to obtain the vehicle operation risk value.

7. The method according to any one of claims 1 to 6, characterized in that, The method further includes: The risk level is obtained by classifying the vehicle operation risk value based on a preset risk threshold. Based on the risk level, corresponding warning information is output to the driving object or driving system, and an avoidance strategy is predicted based on the warning information through artificial intelligence algorithms.

8. A vehicle operation risk quantification assessment device, characterized in that, The device includes: The risk field morphology module is used to obtain the risk field morphology extracted from the road environment when the target vehicle is in motion; The risk field boundary module is used to determine the safety range boundary based on the risk field morphology and construct the risk field boundary model. The risk quantification module is used to perform risk quantification assessment on the risk field boundary model based on the spring model to obtain the vehicle operation risk value.

9. An electronic device, characterized in that, The electronic device includes a memory and a processor, the memory storing a computer program, and the processor executing the computer program to implement the method according to any one of claims 1 to 7.

10. A computer program product, comprising a computer program, characterized in that, When the computer program is executed by a processor, it implements the method of any one of claims 1 to 7.

Images