Network connection vehicle information prompting method considering scene risk degree

Abstract

The invention relates to the technical field of intelligent networked vehicles, in particular to a networked vehicle information prompting method considering scene risk degree, which comprises the following steps: S1, a vehicle performs multi-source data acquisition on current driving environment information through a sensor module and a V2X communication module of the vehicle, and determines the driving environment information of the vehicle according to the driving environment information; constructing basic space semantic information required for designing the risk place; s2, calculating potential energy of a dynamic risk source and a static risk source based on the basic space semantic information, and superposing the potential energy to obtain a scene global risk potential field; s3, calculating a risk field force based on the scene global risk potential field, and determining a risk level of the current driving scene based on the risk field force; according to the method, the global risk potential field is constructed, and a two-factor information priority discrimination mechanism and a multi-mode adaptive information interaction strategy are established, so that fine control of information prompt in a complex driving scene is realized.

Description

Technical Field

[0001] This invention relates to the field of intelligent connected vehicle technology, and specifically to a method for providing connected vehicle information prompts that takes into account the risk level of a given scenario. Background Technology

[0002] With the rapid development of intelligent connected vehicle technology, in-vehicle information systems can provide drivers with increasingly rich information, including vehicle status, navigation instructions, driving assistance warnings, and traffic environment perception. However, the surge in information has also brought new challenges: how to efficiently and safely convey this information to drivers in complex driving scenarios and avoid information overload from negatively impacting driving safety.

[0003] Traditional vehicle information display methods suffer from two technical bottlenecks: firstly, they lack a robust information prioritization mechanism. Intelligent IoT vehicles generally rely on fixed rules or simple threshold judgments in the arrangement and presentation of prompts, failing to dynamically adjust based on the importance, urgency, and risk level of driving tasks. The same type of information should have different priorities in different driving task scenarios (such as following other vehicles, changing lanes, passing through intersections, navigation decisions, etc.), but existing systems cannot achieve real-time priority rearrangement based on changes in tasks. This results in some key prompts not being presented at the appropriate time, while secondary information may occupy visual and cognitive resources, thereby affecting the driver's perception efficiency of key information and reducing overall interaction safety. Secondly, there is a lack of consideration for different information interaction strategies based on the risk level of driving scenarios: Most current systems adopt static prompting strategies, failing to dynamically adjust the amount of information, presentation method, and prompting intensity according to the risk level of the scenario. This results in information overload and interference in high-risk situations, as well as insufficient prominence of key alarms. This not only limits the system's environmental adaptability but also directly weakens the effectiveness of prompts, posing a security risk. Summary of the Invention

[0004] This invention addresses the technical problems existing in the prior art by providing a method for providing connected vehicle information prompts that takes into account the level of scenario risk.

[0005] The technical solution of this invention to solve the above-mentioned technical problems is as follows: A method for providing information prompts for connected vehicles that considers scenario risk levels, comprising the following steps: S1. The vehicle collects multi-source data on the current driving environment through its own sensor module and V2X communication module, and constructs the basic spatial semantic information required for designing the risk field based on the driving environment information. S2. Based on the aforementioned basic spatial semantic information, calculate the potential energy of dynamic risk sources and static risk sources, and superimpose them to obtain the global risk potential field of the scene. S3. Based on the global risk potential field of the scenario, calculate the risk field force, and determine the risk level of the current driving scenario based on the risk field force; S4. Based on the current driving task status and the global risk potential field of the scenario, perform information priority judgment and determine the priority of the information to be prompted; S5. Determine the maximum number of information to be presented based on the risk level of the current driving scenario, and generate and execute an adaptive information interaction strategy based on the priority of the information to be prompted and the maximum number of information to be presented.

[0006] In a preferred embodiment, in step S1, multi-dimensional data is synchronously acquired through the vehicle's own sensor module and V2X communication module. The multi-dimensional data includes the vehicle's own status, information of surrounding traffic participants, road structure information, static obstacles, traffic control information, and external environmental factors. The collected raw multi-dimensional information is standardized and fused. First, through coordinate system transformation, all elements from different sensors and coordinate systems are uniformly mapped to the vehicle local coordinate system centered on the vehicle. Through time synchronization and interpolation, the timing misalignment caused by the difference in acquisition frequency and delay of different sensors is calibrated to ensure that all data correspond to the same moment. Then, through feature cleaning and standardization, outlier removal, noise filtering and missing value processing are performed to obtain a standardized feature set. Based on the acquired standardized feature set, all objects in the driving scenario are divided into three categories: dynamic risk sources, static risk sources, and environmental risk factors.

[0007] In a preferred embodiment, in step S2, a dynamic risk source risk field is constructed based on the semantic information of the classified dynamic risk sources. First, the distance potential energy function is calculated. The value of the distance potential energy function decreases exponentially with the increase of the Euclidean distance between the vehicle and the target. The attenuation rate is controlled by the risk diffusion radius parameter. The specific calculation formula is as follows: ; in, Let represent the distance potential energy function, and d represent the Euclidean distance between the vehicle and the target. Indicates the radius of risk diffusion; Next, the influence function based on relative speed is calculated. This function transforms the speed difference between the vehicle and the target along the line connecting their centers into a weighting factor between 0 and 1. A larger speed difference indicates a larger weighting factor, representing the urgency of the kinetic conflict. The specific calculation formula is as follows: ; in, The function representing the influence of relative velocity. , Indicates the speed of this vehicle. Indicates the target speed. This represents the unit vector pointing from the vehicle to the target. Indicates relative approximate speed. This represents the speed sensitivity coefficient; A heading difference factor is introduced, which is weighted by a function related to the cosine of the heading angle between the vehicle and the target. When the target is directly facing the direction of the vehicle's movement, the heading difference factor increases, indicating a potential risk of head-on collision. The specific calculation formula is as follows: ; in, Indicates the heading difference factor. This represents the sensitivity to the control angle, and cos represents the cosine function. It represents the difference in heading angle between the vehicle and the target object, that is, the angle between the direction of motion of the vehicle and the direction of motion of the target object; Finally, the approach angle factor is calculated to further filter targets whose direction of motion is towards the vehicle. The specific calculation formula is as follows: ; in, Indicates the proximity angle factor. This represents the angle between the target's direction of motion and the vehicle's direction of travel to the target. The dynamic target comprehensive risk potential energy is obtained by comprehensively calculating the distance potential energy function, the relative velocity influence function, the heading difference factor, and the approach angle factor. The specific calculation formula is as follows: ; in, This represents the comprehensive risk potential of a dynamic target; For the identified static risk sources, the equivalent strength and equivalent mass of the static risk source are calculated based on its physical mass, object type, and object shape. The specific calculation formula is as follows: ; in, This represents the equivalent quality of a static risk source. The mass of object q is represented by... Indicates the type of object q. The shape of object q is represented. The real-time position of the vehicle in the same local coordinate system is obtained. Based on the position coordinates of the vehicle and the position coordinates of the static risk source, the distance vector between them is calculated. The specific calculation formula is as follows: ; in, Represents the distance vector. , Let x and y represent the position coordinates of object q, and let x and y represent the horizontal and vertical coordinates of the vehicle in the local coordinate system. A road condition factor is introduced to quantify the impact of environmental conditions on static risk performance. The road condition factor is calculated by acquiring real-time road visibility information, road slope, and road surface adhesion coefficient. The specific calculation formula is as follows: ; ; ; in, Let k represent the road condition factor and k represent the visibility factor. Indicates the road slope factor. Indicates the road adhesion coefficient. , This represents the correction factor. , Indicates the calibration value. This represents the road visibility distance factor. Indicates the road color difference factor. Indicates the slope angle. Indicates the speed of a static risk source; The calculated dynamic risk source risk field is linearly superimposed with the static risk source risk field to obtain the global risk potential field of the scenario. The specific calculation formula is as follows: ; in, This represents the global risk potential field of the scenario.

[0008] In a preferred embodiment, in step S3, the global risk potential field of the scene is a continuous scalar function with respect to spatial location, describing the risk potential energy at any point. The specific calculation formula for the risk field force at the current location is as follows: ; in, Indicates the location Risk field force at the location, This represents the vehicle's position coordinate vector in a two-dimensional plane. Indicates the location The overall risk potential field in the given scenario. This represents the negative gradient of the global risk potential field in the scenario. This represents the partial derivative of the global risk potential field of the scenario with respect to the coordinate x. This represents the partial derivative of the global risk potential field of the scene with respect to the coordinate y. This represents the unit vector in the positive x-axis direction in the vehicle's local coordinate system. It represents the unit vector in the positive y-axis direction in the vehicle's local coordinate system. The calculated risk field force points in the direction that causes the risk potential energy to increase the fastest, that is, it points to the most important potential risk source. The magnitude of the risk field force directly characterizes the combined risk exerted by all risk sources on a specific spatial point. The larger the value, the more severe the risk situation at that point and the more drastic the risk changes. A risk intensity is obtained by calculating the magnitude of the risk field force at the vehicle's current location. The specific calculation formula is as follows: ; in, Indicates the intensity of risk; Traverse the entire driving environment area to find the maximum value of the magnitude of the risk intensity risk field force at all calculation points. Compare the maximum value of the magnitude of the risk field force with the preset first threshold, second threshold, and third threshold. When the maximum value of the magnitude of the risk field force is lower than the first threshold, it is classified as Level 1 risk. When the maximum value of the magnitude of the risk field force is between the first and second thresholds, it is classified as Level 2 risk. When the maximum value of the magnitude of the risk field force is higher than the second threshold and less than or equal to the third threshold, it is classified as Level 3 risk. When the maximum value of the magnitude of the risk field force is greater than the third threshold, it is classified as Level 4 risk.

[0009] In a preferred embodiment, in step S4, the task relevance weight is determined based on the current driving task status. According to the information-task matching degree matrix, the relevance level of each piece of information to be prompted and the current task is queried. The relevance level is qualitatively divided into high, medium, and low. The qualitative level is then converted into a quantitative task relevance weight, which can be specifically expressed as follows: ; in, This represents the j-th message. Indicates the current driving task status; By utilizing the global risk potential field and risk force of the scene, the spatial location of the time described by each piece of information in the risk potential field is determined, and the magnitude of the risk force at that spatial location is obtained. The magnitude of the risk force directly quantifies the local risk intensity. The risk intensity value is input into a nonlinear mapping function for standardization and smoothing, and the prompt priority factor is calculated. The specific calculation formula is as follows: ; in, This indicates a priority factor. The risk field force represents the location of the information in the field, a, b, This represents a constant. The final priority of each piece of information is determined by a weighted sum of task relevance weights and cue priority factors. The specific calculation formula is as follows: ; Where P represents the final priority of each piece of information. , This represents the first harmonic coefficient and the second harmonic coefficient.

[0010] In a preferred embodiment, in step S5, the maximum amount of information currently allowed to be presented is determined based on the risk level. When the scene is determined to be at level one risk, the maximum amount of information presented is... The maximum number of information items presented under Level 2 risk is The maximum number of information items that can be presented under Level 3 risk is: The maximum number of information items that can be presented under Level 4 risk is: ; According to priority Sort all information and truncate the results based on the sorting. The valid information is displayed, and the priority P is divided into 4 levels: first-level priority information is prompted with multimodal mode, second-level priority information is prompted with single-modal mode, third-level priority information is not prompted, and fourth-level priority information is not prompted. For each piece of information to be presented, its display duration is calculated based on its priority using a monotonically increasing function between the shortest and longest prompt times. The specific calculation formula is as follows: ; in, Indicates the duration to be displayed. This indicates the priority of the j-th message. Indicates the maximum prompt time. Indicates the shortest notification time. This indicates a regulatory factor.

[0011] The beneficial effects of this invention are: by constructing a global risk potential field, establishing a two-factor information priority discrimination mechanism, and a multimodal adaptive information interaction strategy, this invention achieves refined control of information prompts in complex driving scenarios; By utilizing a two-factor priority discrimination mechanism that correlates risk field forces with driving tasks, information prompts can be dynamically matched with the current task and risk situation. The content and priority of information display can be automatically adjusted according to changes in the scenario, thereby improving the effectiveness and acceptability of the prompts. Based on risk level control, the amount of information, the form of prompts, and the duration of display are adjusted to avoid excessive cognitive load on drivers due to too much information. In high-risk, high-task-load scenarios, key prompts are presented first, and multimodal prompts enhance perception capabilities and improve driving safety. Attached Figure Description

[0012] Figure 1 This is a flowchart of the present invention; Figure 2 This is a technical roadmap of the present invention; Figure 3 This is a scenario risk calculation diagram for the present invention; Figure 4 This is a diagram illustrating the information interaction strategy of the present invention. Detailed Implementation

[0013] The technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, and not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0014] In the description of this application, the terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of indicated technical features. Thus, a feature defined as "first" or "second" may explicitly or implicitly include one or more of the stated features. In the description of this application, "multiple" means two or more, unless otherwise explicitly specified.

[0015] In the description of this application, the term "for example" is used to mean "used as an example, illustration, or description." Any embodiment described as "for example" in this application is not necessarily to be construed as being more preferred or advantageous than other embodiments. The following description is provided to enable any person skilled in the art to make and use the invention. Details are set forth in the following description for purposes of explanation. It should be understood that those skilled in the art will recognize that the invention can be made without using these specific details. In other instances, well-known structures and processes will not be described in detail to avoid obscuring the description of the invention with unnecessary detail. Therefore, the invention is not intended to be limited to the embodiments shown, but is consistent with the broadest scope of the principles and features disclosed in this application.

[0016] like Figures 1-4 This embodiment provides a method for providing connected vehicle information prompts that considers scenario risk levels, comprising the following steps: S1. The vehicle collects multi-source data on the current driving environment through its own sensor module and V2X communication module, and constructs the basic spatial semantic information required for designing the risk field based on the driving environment information. Furthermore, through the vehicle's own sensor modules and V2X communication modules, multi-dimensional data is acquired synchronously. This multi-dimensional data includes the vehicle's own status (position, speed, acceleration, heading angle, vehicle size), information on surrounding traffic participants (nearby vehicle positions, relative speed, acceleration, trajectory prediction, pedestrian and non-motorized vehicle motion characteristics), road structure information (lane lines, road curvature, lane width, road type), static obstacles (guardrails, medians, curbs, fixed buildings), traffic control information (traffic lights, signs, markings), and external environmental factors (weather, lighting, visibility, road surface adhesion coefficient). The collected raw multi-dimensional information is standardized and fused. First, through coordinate system transformation, all elements from different sensors and coordinate systems are uniformly mapped to the vehicle local coordinate system centered on the vehicle. Through time synchronization and interpolation, the timing misalignment caused by the difference in acquisition frequency and delay of different sensors is calibrated to ensure that all data correspond to the same moment. Then, through feature cleaning and standardization, outlier removal, noise filtering and missing value processing are performed to obtain a standardized feature set. Based on the acquired standardized feature set, all objects in the driving scenario are divided into three categories: dynamic risk sources, such as vehicles, pedestrians, and cyclists, whose risks mainly come from the relative movement of the vehicle and the interaction intent; static risk sources, such as road boundaries, guardrails, and fixed obstacles, whose risks mainly come from spatial constraints; and environmental risk factors, such as low-adhesion road surfaces and weather, whose risks mainly manifest as a global impact on the vehicle or perception capabilities.

[0017] S2. Based on the aforementioned basic spatial semantic information, calculate the potential energy of dynamic risk sources and static risk sources, and superimpose them to obtain the global risk potential field of the scene. Furthermore, based on the semantic information of the classified dynamic risk sources, a dynamic risk source risk field is constructed. First, the distance potential energy function is calculated. The value of the distance potential energy function decreases exponentially with the increase of the Euclidean distance between the vehicle and the target. The decay rate is controlled by the risk diffusion radius parameter. The specific calculation formula is as follows: ; in, Let represent the distance potential energy function, and d represent the Euclidean distance between the vehicle and the target. Indicates the radius of risk diffusion; Next, the influence function based on relative speed is calculated. This function transforms the speed difference between the vehicle and the target along the line connecting their centers into a weighting factor between 0 and 1. A larger speed difference indicates a larger weighting factor, representing the urgency of the kinetic conflict. The specific calculation formula is as follows: ; in, The function representing the influence of relative velocity. , Indicates the speed of this vehicle. Indicates the target speed. This represents the unit vector pointing from the vehicle to the target. Indicates relative approximate speed. This represents the speed sensitivity coefficient; A heading difference factor is introduced, which is weighted by a function related to the cosine of the heading angle between the vehicle and the target. When the target is directly facing the direction of the vehicle's movement, the heading difference factor increases, indicating a potential risk of head-on collision. The specific calculation formula is as follows: ; in, Indicates the heading difference factor. This indicates the sensitivity to the control angle, used to adjust the amplification factor of the effect of heading differences on the weighting factor. The larger the value, the more sensitive it is to heading differences; that is, the same heading difference will result in a larger heading difference factor value. cos represents the cosine function. It represents the difference in heading angle between the vehicle and the target object, that is, the angle between the direction of motion of the vehicle and the direction of motion of the target object; Finally, the approach angle factor is calculated to further filter targets whose direction of motion is towards the vehicle. The specific calculation formula is as follows: ; in, Indicates the proximity angle factor. This represents the angle between the target's direction of motion and the vehicle's direction of travel to the target. The dynamic target comprehensive risk potential energy is obtained by comprehensively calculating the distance potential energy function, the relative velocity influence function, the heading difference factor, and the approach angle factor. The specific calculation formula is as follows: ; in, This represents the comprehensive risk potential of a dynamic target; For the identified static risk sources, the equivalent strength and equivalent mass of the static risk source are calculated based on its physical mass, object type, and object shape. The specific calculation formula is as follows: ; in, This represents the equivalent quality of a static risk source. The mass of object q is represented by... Indicates the type of object q. The shape of object q is represented. The real-time position of the vehicle in the same local coordinate system is obtained. Based on the position coordinates of the vehicle and the position coordinates of the static risk source, the distance vector between them is calculated. The specific calculation formula is as follows: ; in, Represents the distance vector. , Let x and y represent the position coordinates of object q, and let x and y represent the horizontal and vertical coordinates of the vehicle in the local coordinate system. A road condition factor is introduced to quantify the impact of environmental conditions on static risk performance. The road condition factor is calculated by acquiring real-time road visibility information, road slope, and road surface adhesion coefficient. The specific calculation formula is as follows: ; ; ; in, Let k represent the road condition factor and k represent the visibility factor. Indicates the road slope factor. Indicates the road adhesion coefficient. , This represents the correction factor. , Indicates the calibration value. This represents the road visibility distance factor. Indicates the road color difference factor. Indicates the slope angle. The velocity of a static risk source is used to determine whether it is an absolutely stationary object or a movable stationary object. The calculated dynamic risk source risk field is linearly superimposed with the static risk source risk field to obtain the global risk potential field of the scenario. The specific calculation formula is as follows: ; in, The scenario-wide risk potential field represents the scalar superposition of the risk fields of dynamic and static risk sources. The scenario-wide risk potential field can comprehensively reflect the total risk impact from all static and dynamic risk sources at any point in space.

[0018] S3. Based on the global risk potential field of the scenario, calculate the risk field force, and determine the risk level of the current driving scenario based on the risk field force; Furthermore, the global risk potential field of the scene is a continuous scalar function with respect to spatial location, describing the risk potential energy at any point. The specific calculation formula for the risk field force at the current location is obtained by calculating the negative gradient of the scalar function, as follows: ; in, Indicates the location The risk field force at a given location describes the magnitude and direction of the force exerted by the global risk potential field of the scene on driving behavior at that point. This represents the vehicle's position coordinate vector in a two-dimensional plane. Indicates the location The overall risk potential field in the given scenario. This represents the negative gradient of the global risk potential field of the scene. The direction of the gradient is the direction in which the potential energy increases the fastest, therefore the direction of the negative gradient is the direction in which the potential energy decreases the fastest, pointing towards the danger direction. Its magnitude represents the distance intensity of the potential energy change. This represents the partial derivative of the global risk potential field of the scenario with respect to the coordinate x. This represents the partial derivative of the global risk potential field of the scene with respect to the coordinate y. This represents the unit vector in the positive x-axis direction in the vehicle's local coordinate system. It represents the unit vector in the positive y-axis direction in the vehicle's local coordinate system. The calculated risk field force points in the direction that causes the risk potential energy to increase the fastest, that is, it points to the most important potential risk source. The magnitude of the risk field force directly characterizes the combined risk exerted by all risk sources on a specific spatial point. The larger the value, the more severe the risk situation at that point and the more drastic the risk changes. A risk intensity is obtained by calculating the magnitude of the risk field force at the vehicle's current location. The specific calculation formula is as follows: ; in, Indicates the intensity of risk; Traverse the entire driving environment area to find the maximum value of the magnitude of the risk intensity risk field force at all calculation points. Compare the maximum value of the magnitude of the risk field force with the preset first threshold, second threshold, and third threshold. When the maximum value of the magnitude of the risk field force is lower than the first threshold, it is classified as Level 1 risk. When the maximum value of the magnitude of the risk field force is between the first and second thresholds, it is classified as Level 2 risk. When the maximum value of the magnitude of the risk field force is higher than the second threshold and less than or equal to the third threshold, it is classified as Level 3 risk. When the maximum value of the magnitude of the risk field force is greater than the third threshold, it is classified as Level 4 risk.

[0019] S4. Based on the current driving task status and the global risk potential field of the scenario, perform information priority judgment and determine the priority of the information to be prompted; Furthermore, based on the current driving task status, task relevance weights are determined. According to the information-task matching matrix, the relevance level of each piece of information to be prompted and the current task is queried. The relevance levels are qualitatively divided into high, medium, and low. These qualitative levels are then converted into quantitative task relevance weights, specifically as follows: ; in, This represents the j-th message. Indicates the current driving task status; By utilizing the global risk potential field and risk force of the scene, the spatial location of the time described by each piece of information in the risk potential field is determined, and the magnitude of the risk force at that spatial location is obtained. The magnitude of the risk force directly quantifies the local risk intensity. The risk intensity value is input into a nonlinear mapping function for standardization and smoothing, and the prompt priority factor is calculated. The specific calculation formula is as follows: ; in, This indicates a priority factor. The risk field force represents the location of the information in the field, a, b, This represents a constant. The final priority of each piece of information is determined by a weighted sum of task relevance weights and cue priority factors. The specific calculation formula is as follows: ; Where P represents the final priority of each piece of information. , The first and second harmonic coefficients are used to adjust the relative weight of task requirements and risk urgency in the final decision. An information priority sequence is obtained by calculating the final priority of each piece of information. The information priority sequence ensures that resources are presented first in high task load scenarios.

[0020] S5. Determine the maximum number of information to be presented based on the risk level of the current driving scenario, and generate and execute an adaptive information interaction strategy based on the priority of the information to be prompted and the maximum number of information to be presented.

[0021] Furthermore, the maximum amount of information allowed to be presented is determined based on the risk level. When the scenario is classified as Level 1 risk, the maximum amount of information presented is [missing information]. The maximum number of information items presented under Level 2 risk is The maximum number of information items that can be presented under Level 3 risk is: The maximum number of information items that can be presented under Level 4 risk is: ; According to priority Sort all information and truncate the results based on the sorting. The valid information is displayed, and the priority P is divided into 4 levels: first-level priority information is prompted with multimodal mode, second-level priority information is prompted with single-modal mode, third-level priority information is not prompted, and fourth-level priority information is not prompted. For each piece of information to be presented, its display duration is calculated based on its priority using a monotonically increasing function between the shortest and longest prompt times. The specific calculation formula is as follows: ; in, Indicates the duration to be displayed. This indicates the priority of the j-th message. Indicates the maximum prompt time. Indicates the shortest notification time. This indicates a regulatory factor.

[0022] It should be noted that the descriptions of each embodiment in the above embodiments have different focuses. For parts that are not described in detail in a certain embodiment, please refer to the relevant descriptions in other embodiments.

[0023] Those skilled in the art will understand that embodiments of the present invention can be provided as methods, systems, or computer program products. Therefore, the present invention can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present invention can take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0024] This invention is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded computer, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart illustrations. Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0025] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0026] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0027] Although preferred embodiments of the invention have been described, those skilled in the art, upon learning the basic inventive concept, can make other changes and modifications to these embodiments. Therefore, the appended claims are intended to be interpreted as including both the preferred embodiments and all changes and modifications falling within the scope of the invention.

[0028] Obviously, those skilled in the art can make various modifications and variations to this invention without departing from its spirit and scope. Therefore, if these modifications and variations fall within the scope of the claims of this invention and their equivalents, this invention also intends to include these modifications and variations.

Claims

1. A method for providing information prompts for connected vehicles that considers scenario risk levels, characterized in that, Includes the following steps: S1. The vehicle collects multi-source data on the current driving environment through its own sensor module and V2X communication module, and constructs the basic spatial semantic information required for designing the risk field based on the driving environment information. S2. Based on the aforementioned basic spatial semantic information, calculate the potential energy of dynamic risk sources and static risk sources, and superimpose them to obtain the global risk potential field of the scene. S3. Based on the global risk potential field of the scenario, calculate the risk field force, and determine the risk level of the current driving scenario based on the risk field force; S4. Based on the current driving task status and the global risk potential field of the scenario, perform information priority judgment and determine the priority of the information to be prompted; S5. Determine the maximum number of information to be presented based on the risk level of the current driving scenario, and generate and execute an adaptive information interaction strategy based on the priority of the information to be prompted and the maximum number of information to be presented.

2. The method for providing connected vehicle information prompts considering scenario risk level according to claim 1, characterized in that, In S1, multi-dimensional data is acquired synchronously through the vehicle's own sensor module and V2X communication module. The multi-dimensional data includes the vehicle's own status, information of surrounding traffic participants, road structure information, static obstacles, traffic control information, and external environmental factors. The collected raw multi-dimensional information is standardized and fused. First, through coordinate system transformation, all elements from different sensors and coordinate systems are uniformly mapped to the vehicle local coordinate system centered on the vehicle. Through time synchronization and interpolation, the timing misalignment caused by the difference in acquisition frequency and delay of different sensors is calibrated to ensure that all data correspond to the same moment. Then, through feature cleaning and standardization, outlier removal, noise filtering and missing value processing are performed to obtain a standardized feature set. Based on the acquired standardized feature set, all objects in the driving scenario are divided into three categories: dynamic risk sources, static risk sources, and environmental risk factors.

3. The method for providing connected vehicle information prompts considering scenario risk as described in claim 1, characterized in that, In step S2, a dynamic risk field is constructed based on the semantic information of the classified dynamic risk sources. First, the distance potential energy function is calculated. The value of the distance potential energy function decreases exponentially with the increase of the Euclidean distance between the vehicle and the target. The decay rate is controlled by the risk diffusion radius parameter. The specific calculation formula is as follows: ； in, Let represent the distance potential energy function, and d represent the Euclidean distance between the vehicle and the target. Indicates the radius of risk diffusion; Next, the influence function based on relative speed is calculated. This function transforms the speed difference between the vehicle and the target along the line connecting their centers into a weighting factor between 0 and 1. A larger speed difference indicates a larger weighting factor, representing the urgency of the kinetic conflict. The specific calculation formula is as follows: ； in, The function representing the influence of relative velocity. , Indicates the speed of this vehicle. Indicates the target speed. This represents the unit vector pointing from the vehicle to the target. Indicates relative approximate speed. This represents the speed sensitivity coefficient; A heading difference factor is introduced, which is weighted by a function related to the cosine of the heading angle between the vehicle and the target. When the target is directly facing the direction of the vehicle's movement, the heading difference factor increases, indicating a potential risk of head-on collision. The specific calculation formula is as follows: ； in, Indicates the heading difference factor. This represents the sensitivity to the control angle, and cos represents the cosine function. It represents the difference in heading angle between the vehicle and the target object, that is, the angle between the direction of motion of the vehicle and the direction of motion of the target object; Finally, the approach angle factor is calculated to further filter targets whose direction of motion is towards the vehicle. The specific calculation formula is as follows: ； in, Indicates the proximity angle factor. This indicates the angle between the target's direction of motion and the direction from which the vehicle moves to the target; The dynamic target comprehensive risk potential energy is obtained by comprehensively calculating the range potential energy function, the relative velocity influence function, the heading difference factor, and the approach angle factor. The specific calculation formula is as follows: ； in, It represents the comprehensive risk potential of a dynamic target.

4. The method for providing connected vehicle information prompts considering scenario risk as described in claim 1, characterized in that, For the identified static risk sources, the equivalent strength and equivalent mass of the static risk source are calculated based on its physical mass, object type, and object shape. The specific calculation formula is as follows: ； in, This represents the equivalent quality of a static risk source. The mass of object q is represented by... Indicates the type of object q. The shape of object q is represented. The real-time position of the vehicle in the same local coordinate system is obtained. Based on the position coordinates of the vehicle and the position coordinates of the static risk source, the distance vector between them is calculated. The specific calculation formula is as follows: ； in, Represents the distance vector. , Let x and y represent the position coordinates of object q, and let x and y represent the horizontal and vertical coordinates of the vehicle in the local coordinate system. A road condition factor is introduced to quantify the impact of environmental conditions on static risk performance. The road condition factor is calculated by acquiring real-time road visibility information, road slope, and road surface adhesion coefficient. The specific calculation formula is as follows: ； ； ； in, Let k represent the road condition factor and k represent the visibility factor. Indicates the road slope factor. Indicates the road adhesion coefficient. , This represents the correction factor. , Indicates the calibration value. This represents the road visibility distance factor. Indicates the road color difference factor. Indicates the slope angle. This indicates the speed of a static risk source.

5. A method for providing connected vehicle information prompts considering scenario risk levels according to claim 4, characterized in that, The calculated dynamic risk source risk field is linearly superimposed with the static risk source risk field to obtain the global risk potential field of the scenario. The specific calculation formula is as follows: ； in, This represents the global risk potential field of the scenario.

6. The method for providing connected vehicle information prompts considering scenario risk as described in claim 1, characterized in that, In S3, the global risk potential field of the scene is a continuous scalar function with respect to spatial location, describing the risk potential energy at any point. The specific calculation formula for the risk field force at the current location is as follows: ； in, Indicates the location Risk field force at the location, This represents the vehicle's position coordinate vector in a two-dimensional plane. Indicates the location The overall risk potential field in the given scenario. This represents the negative gradient of the global risk potential field in the scenario. This represents the partial derivative of the global risk potential field of the scenario with respect to the coordinate x. This represents the partial derivative of the global risk potential field of the scene with respect to the coordinate y. This represents the unit vector in the positive x-axis direction in the vehicle's local coordinate system. It represents the unit vector in the positive y-axis direction in the vehicle's local coordinate system. The calculated risk field force points in the direction that causes the risk potential energy to increase the fastest, that is, it points to the most important potential risk source.

7. A method for providing connected vehicle information prompts considering scenario risk levels according to claim 6, characterized in that, The magnitude of the risk field force directly characterizes the combined risk exerted by all risk sources on a specific spatial point. The larger the value, the more severe the risk situation at that point and the more drastic the risk changes. A risk intensity is obtained by calculating the magnitude of the risk field force at the vehicle's current location. The specific calculation formula is as follows: ； in, Indicates the intensity of risk; Traverse the entire driving environment area to find the maximum value of the magnitude of the risk intensity risk field force at all calculation points. Compare the maximum value of the magnitude of the risk field force with the preset first threshold, second threshold, and third threshold. When the maximum value of the magnitude of the risk field force is lower than the first threshold, it is classified as Level 1 risk. When the maximum value of the magnitude of the risk field force is between the first and second thresholds, it is classified as Level 2 risk. When the maximum value of the magnitude of the risk field force is higher than the second threshold and less than or equal to the third threshold, it is classified as Level 3 risk. When the maximum value of the magnitude of the risk field force is greater than the third threshold, it is classified as Level 4 risk.

8. A method for providing connected vehicle information prompts considering scenario risk levels according to claim 1, characterized in that, In step S4, the task relevance weight is determined based on the current driving task status. According to the information-task matching matrix, the relevance level of each piece of information to be prompted and the current task is queried. The relevance level is qualitatively divided into high, medium, and low, and this qualitative level is converted into a quantitative task relevance weight, which can be specifically expressed as follows: ； in, This represents the j-th message. Indicates the current driving task status.

9. A method for providing connected vehicle information prompts considering scenario risk levels according to claim 8, characterized in that, By utilizing the global risk potential field and risk force of the scene, the spatial location of the time described by each piece of information in the risk potential field is determined, and the magnitude of the risk force at that spatial location is obtained. The magnitude of the risk force directly quantifies the local risk intensity. The risk intensity value is input into a nonlinear mapping function for standardization and smoothing, and the prompt priority factor is calculated. The specific calculation formula is as follows: ； in, This indicates a priority factor. The risk field force represents the location of the information in the field, a, b, This represents a constant. The final priority of each piece of information is determined by a weighted sum of task relevance weights and cue priority factors. The specific calculation formula is as follows: ； Where P represents the final priority of each piece of information. , This represents the first harmonic coefficient and the second harmonic coefficient.

10. A method for providing connected vehicle information prompts considering scenario risk levels according to claim 1, characterized in that, In step S5, the maximum amount of information allowed to be presented is determined based on the risk level. When the scene is determined to be at level one risk, the maximum amount of information to be presented is... The maximum number of information items presented under Level 2 risk is The maximum number of information items that can be presented under Level 3 risk is: The maximum number of information items that can be presented under Level 4 risk is: ; According to priority Sort all information and truncate the results based on the sorting. The valid information is displayed, and the priority P is divided into 4 levels: first-level priority information is prompted with multimodal mode, second-level priority information is prompted with single-modal mode, third-level priority information is not prompted, and fourth-level priority information is not prompted. For each piece of information to be presented, its display duration is calculated based on its priority using a monotonically increasing function between the shortest and longest prompt times. The specific calculation formula is as follows: ； in, Indicates the duration to be displayed. This indicates the priority of the j-th message. Indicates the maximum prompt time. Indicates the shortest notification time. This indicates a regulatory factor.

Images