Driving behavior risk assessment method, device, equipment and computer program product

Abstract

The application discloses a driving behavior risk assessment method, device, equipment and computer program product, comprising: acquiring vehicle driving parameters, vehicle safety system states, road images and external environmental factors of a target vehicle in a first historical period; identifying multiple target moments of high-risk driving operations of the target vehicle according to the vehicle driving parameters, inputting the vehicle safety system states, road images and external environmental factors corresponding to the target moments into a pre-trained driving scene recognition model to obtain target driving scenes; determining high-risk driving behavior events of the target moments according to the target driving scenes and operation types of the corresponding high-risk driving operations; and assessing a driving behavior risk level of the target vehicle according to the distribution of the high-risk driving behavior events in the first historical period, and generating driving behavior improvement suggestions. The application can help drivers improve driving habits, reduce accident risks and improve driving safety, and can be applied to the technical field of vehicle monitoring.

Description

Technical Field

[0001] This invention relates to the field of vehicle monitoring technology, and in particular to a method, device, equipment, and computer program product for assessing driving behavior risks. Background Technology

[0002] Existing driving behavior assessment technologies are mainly divided into two categories: one is basic data recording schemes, which only collect simple data such as vehicle speed and braking frequency through onboard OBD devices, without in-depth analysis and targeted suggestions. They only achieve data storage and simple statistics, without generating safety reports; the other is basic analysis schemes, which only identify behaviors such as rapid acceleration and sudden braking and give general reminders, lacking monthly summaries, risk classification, and personalized optimization suggestions. For example, the driving score function of some navigation apps on the market is based on a single dimension of scoring and does not take into account the actual working conditions of the vehicle and the driver's habits.

[0003] Furthermore, existing technologies are mostly not linked to vehicle safety systems (such as ABS and ESP), making it impossible to accurately determine the safety of actions (such as emergency braking caused by emergency avoidance versus emergency braking during dangerous driving). Optimization suggestions are mostly generic phrases (such as "safe driving"), lacking actionable improvement steps and long-term tracking mechanisms, failing to reflect changes in driver habits and thus failing to effectively help users improve their driving behavior.

[0004] In summary, current technologies cannot provide a comprehensive analysis and assessment of driving behavior or offer targeted recommendations, making it difficult to effectively help drivers improve their driving habits and reduce accident risks. These issues urgently need to be addressed. Summary of the Invention

[0005] The purpose of this invention is to at least partially solve one of the technical problems existing in the prior art.

[0006] Therefore, one objective of this invention is to provide a driving behavior risk assessment method that enables comprehensive analysis and assessment of driving behavior and generates targeted suggestions, which can effectively help drivers improve driving habits, reduce accident risks, and improve driving safety.

[0007] Another objective of this invention is to provide a driving behavior risk assessment device.

[0008] To achieve the above-mentioned technical objectives, the technical solutions adopted in the embodiments of the present invention include: On one hand, embodiments of the present invention provide a method for assessing driving behavior risks, including the following steps: Acquire the target vehicle's driving parameters, vehicle safety system status, road images, and external environmental factors during the first historical time period; Based on the vehicle driving parameters, identify multiple target moments when the target vehicle engages in high-risk driving operations, and input the vehicle safety system status, the road image, and the external environmental factors corresponding to the target moments into a pre-trained driving scene recognition model to obtain the target driving scene corresponding to the target moments. The high-risk driving behavior event at the target moment is determined based on the target driving scenario and the corresponding high-risk driving operation type. The risk level of the target vehicle's driving behavior during the first historical period is assessed based on the distribution of the high-risk driving behavior events during the first historical period, and corresponding driving behavior improvement suggestions are generated.

[0009] Furthermore, in one embodiment of the present invention, the vehicle driving parameters include vehicle speed, longitudinal acceleration, and lateral acceleration; the high-risk driving operations include rapid acceleration, sudden braking, and sharp turning; and the step of identifying multiple target moments in which the target vehicle engages in high-risk driving operations based on the vehicle driving parameters specifically includes: When the longitudinal acceleration is greater than a preset first threshold, it is determined that the target vehicle is undergoing a rapid acceleration operation, and the corresponding moment is determined as the first target moment; When the longitudinal acceleration is less than a preset second threshold, it is determined that the target vehicle has performed an emergency braking operation, and the corresponding moment is determined as the second target moment; When the lateral acceleration is greater than a preset third threshold and the vehicle speed is greater than a preset fourth threshold, it is determined that the target vehicle is performing a sharp turn, and the corresponding moment is determined as the third target moment.

[0010] Furthermore, in one embodiment of the present invention, the driving scene recognition model is trained through the following steps: Acquire vehicle safety system status samples, road image samples, and external environmental factor samples of the test vehicle during the testing phase, and determine the corresponding driving scenario labels through manual annotation; The vehicle safety system state sample, the road image sample, and the external environmental factor sample are input into a pre-constructed multi-branch fusion neural network to obtain the corresponding predicted driving scenario. The loss value is determined based on the predicted driving scenario and the driving scenario label; The parameters of the multi-branch fusion neural network are updated using the backpropagation algorithm based on the loss value to obtain the trained driving scene recognition model. The multi-branch fusion neural network includes a first MLP layer, a CNN layer, a second MLP layer, a feature fusion layer, and an output layer.

[0011] Furthermore, in one embodiment of the present invention, the step of inputting the vehicle safety system state sample, the road image sample, and the external environmental factor sample into a pre-constructed multi-branch fusion neural network to obtain the corresponding predicted driving scenario specifically includes: The vehicle safety system state sample is input into the first MLP layer for feature mapping to obtain the safety system state features; The road image samples are input into the CNN layer for feature extraction to obtain road condition features; The external environmental factor samples are input into the second MLP layer for feature mapping to obtain environmental factor features; The feature fusion layer performs feature fusion on the safety system state features, road condition features, and environmental factor features based on a self-attention mechanism to obtain a fused feature vector. The output layer maps the fused feature vector to the predicted driving scenario.

[0012] Furthermore, in one embodiment of the present invention, determining the high-risk driving behavior event at the target moment based on the target driving scenario and the corresponding high-risk driving operation type specifically includes: Determine scene labels based on the target driving scenario, and determine operation type labels based on the operation type of the corresponding high-risk driving operation; The scene label and the operation type label are integrated to obtain the high-risk driving behavior label at the target time, and the corresponding high-risk driving behavior event is determined based on the high-risk driving behavior label.

[0013] Furthermore, in one embodiment of the present invention, the step of assessing the driving behavior risk level of the target vehicle during the first historical period based on the distribution of the high-risk driving behavior events during the first historical period specifically includes: The number of occurrences, minimum time intervals, and maximum severity of each high-risk driving behavior event within the first historical period were statistically analyzed. The event risk score of the high-risk driving behavior event is calculated based on the number of occurrences, the minimum time interval, and the maximum severity. Determine the event risk coefficient of each of the high-risk driving behavior events, and perform a weighted summation of the event risk scores of each of the high-risk driving behavior events based on the event risk coefficients to obtain the total driving behavior risk score of the target vehicle in the first historical period. The driving behavior risk level is determined based on the overall driving behavior risk score.

[0014] Furthermore, in one embodiment of the present invention, the generation of corresponding driving behavior improvement suggestions specifically includes: Based on the event risk score, several driving behavior events to be optimized are selected from the high-risk driving behavior events; The driving behavior improvement suggestions are generated based on the operation type and driving scenario corresponding to the driving behavior event to be optimized.

[0015] On the other hand, embodiments of the present invention provide a driving behavior risk assessment device, comprising: The data acquisition module is used to acquire the target vehicle's driving parameters, vehicle safety system status, road images, and external environmental factors during the first historical period. The driving scene recognition module is used to identify multiple target moments when the target vehicle has high-risk driving operations based on the vehicle driving parameters, and input the vehicle safety system status, the road image and the external environmental factors corresponding to the target moments into a pre-trained driving scene recognition model to obtain the target driving scene corresponding to the target moments. The high-risk driving behavior event determination module is used to determine the high-risk driving behavior event at the target moment based on the target driving scenario and the operation type of the corresponding high-risk driving operation. The driving behavior risk level assessment module is used to assess the driving behavior risk level of the target vehicle in the first historical period based on the distribution of the high-risk driving behavior events in the first historical period, and generate corresponding driving behavior improvement suggestions.

[0016] On the other hand, embodiments of the present invention provide an electronic device, including: At least one processor; At least one memory for storing at least one program; When the at least one program is executed by the at least one processor, the at least one processor implements the above-described method for assessing driving behavior risks.

[0017] On the other hand, embodiments of the present invention also provide a computer-readable storage medium storing a processor-executable computer program that, when executed by a processor, implements the aforementioned driving behavior risk assessment method.

[0018] On the other hand, embodiments of the present invention also provide a computer program product, including a computer program that, when executed by a processor, implements the above-described method for assessing driving behavior risks.

[0019] The advantages and beneficial effects of the present invention will be set forth in part in the description which follows, and in part will be obvious from the description, or may be learned by practice of the invention: This invention acquires vehicle driving parameters, vehicle safety system status, road images, and external environmental factors of a target vehicle during a first historical time period. Based on the vehicle driving parameters, it identifies multiple target moments where the target vehicle engages in high-risk driving operations. The vehicle safety system status, road images, and external environmental factors corresponding to these target moments are input into a pre-trained driving scenario recognition model to obtain the target driving scenario corresponding to each target moment. Based on the target driving scenario and the operation type of the corresponding high-risk driving operation, high-risk driving behavior events are determined for each target moment. The distribution of these high-risk driving behavior events during the first historical time period is used to assess the driving behavior risk level of the target vehicle during that period, and corresponding driving behavior improvement suggestions are generated. This invention identifies target moments with high-risk driving operations based on vehicle driving parameters, and then identifies corresponding target driving scenarios based on the vehicle safety system status, road images, and external environmental factors at those target moments. This allows for the accurate reconstruction of real high-risk driving behavior events based on the target driving scenario and the operation type of the high-risk driving operation. Furthermore, the distribution of these high-risk driving behavior events is used to assess the driving behavior risk level of the target vehicle. This comprehensive analysis and evaluation of driving behavior, along with the generation of targeted suggestions, effectively helps drivers improve driving habits, reduce accident risks, and enhance driving safety. Attached Figure Description

[0020] To more clearly illustrate the technical solutions in the embodiments of the present invention, the drawings used in the embodiments of the present invention are described below. It should be understood that the drawings described below are only for the convenience of clearly describing some embodiments of the technical solutions of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0021] Figure 1 A flowchart illustrating the steps of a driving behavior risk assessment method provided in this embodiment of the invention; Figure 2 A structural block diagram of a driving behavior risk assessment device provided in an embodiment of the present invention; Figure 3 This is a structural block diagram of an electronic device provided in an embodiment of the present invention. Detailed Implementation

[0022] To make the objectives, technical solutions, and advantages of this invention clearer, the invention will be further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention. 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 the embodiments of this invention; they are merely examples of apparatuses and methods consistent with some aspects of the embodiments of this invention as detailed in the appended claims.

[0023] 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 invention pertains. The terminology used herein is for the purpose of describing embodiments of the invention only and is not intended to limit the invention.

[0024] The driving behavior risk assessment method provided in this invention can be applied to a terminal, a server, or software running on a terminal or 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 that implements the driving behavior risk assessment method, but is not limited to the above forms.

[0025] This invention 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, network PCs, minicomputers, mainframe computers, and distributed computing environments including any of the above systems or devices. This invention can be described in the general context of computer-executable instructions, such as program modules, that are executed by a computer. Generally, program modules include routines, programs, objects, components, data structures, etc., that perform specific tasks or implement specific abstract data types. This invention 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.

[0026] It should be noted that in various specific embodiments of the present invention, 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 the present invention require access to sensitive personal information of users, separate permission or consent from the user is obtained through pop-ups or redirection to a confirmation page. Only after obtaining the user's separate permission or consent is the necessary user-related data for the normal operation of the embodiments of the present invention acquired.

[0027] Reference Figure 1 This invention provides a method for assessing driving behavior risks, specifically including the following steps: S101. Obtain the target vehicle's driving parameters, vehicle safety system status, road images, and external environmental factors during the first historical period. S102. Identify multiple target moments when the target vehicle engages in high-risk driving operations based on vehicle driving parameters, and input the vehicle safety system status, road image, and external environmental factors corresponding to the target moments into a pre-trained driving scene recognition model to obtain the target driving scene corresponding to the target moments. S103. Determine the high-risk driving behavior events at the target time based on the target driving scenario and the corresponding high-risk driving operation type. S104. Assess the risk level of the target vehicle's driving behavior in the first historical period based on the distribution of high-risk driving behavior events in the first historical period, and generate corresponding driving behavior improvement suggestions.

[0028] This invention identifies target moments of high-risk driving operations based on vehicle driving parameters. Then, it identifies corresponding target driving scenarios based on the vehicle safety system status, road images, and external environmental factors at the target moment. This allows for the accurate reconstruction of real high-risk driving behavior events based on the target driving scenario and the type of high-risk driving operation. Furthermore, it assesses the driving behavior risk level of the target vehicle based on the distribution of high-risk driving behavior events. This enables a comprehensive analysis and evaluation of driving behavior and the generation of targeted suggestions, effectively helping drivers improve driving habits, reduce accident risks, and enhance driving safety.

[0029] As a further optional implementation, vehicle driving parameters include vehicle speed, longitudinal acceleration, and lateral acceleration; high-risk driving operations include rapid acceleration, sudden braking, and sharp turning; and multiple target moments when the target vehicle engages in high-risk driving operations are identified based on the vehicle driving parameters, specifically including: S1021. When the longitudinal acceleration is greater than the preset first threshold, it is determined that the target vehicle has a rapid acceleration operation, and the corresponding time is determined as the first target time. S1022. When the longitudinal acceleration is less than the preset second threshold, it is determined that the target vehicle has performed an emergency braking operation, and the corresponding time is determined as the second target time. S1023. When the lateral acceleration is greater than the preset third threshold and the vehicle speed is greater than the preset fourth threshold, it is determined that the target vehicle is performing a sharp turn, and the corresponding time is determined as the third target time.

[0030] Specifically, embodiments of the present invention achieve comprehensive collection of multi-dimensional driving data through a data acquisition module, including: 1) Vehicle driving parameter acquisition unit: Collects parameters such as vehicle speed, longitudinal acceleration (for rapid acceleration / braking determination), lateral acceleration (for sharp turning determination), braking force, steering angle, driving time, and driving mileage through on-board sensors. The sampling frequency is 10Hz to ensure data accuracy. 2) Operating Condition and Safety System Data Unit: Collects road images, vehicle safety system status (whether ABS / ESP is triggered, used to distinguish between emergency avoidance and dangerous driving), and environmental factors (temperature, rain / sunny weather, etc.). 3) Data synchronization unit: Multi-dimensional data is stored synchronously according to timestamps to ensure the correlation between behavior and working conditions and environmental data, providing a foundation for subsequent accurate analysis.

[0031] This invention accurately identifies unsafe high-risk driving operations based on vehicle driving parameters. Specifically, it sets clear criteria for judging high-risk driving operations, classifying them into three core types: rapid acceleration, sudden braking, and sharp turning. When the longitudinal acceleration is greater than a preset first threshold (e.g., 0.8g), the target vehicle is determined to have performed a rapid acceleration operation. When the longitudinal acceleration is less than a preset second threshold (e.g., -0.7g), the target vehicle is determined to have performed a sudden braking operation. When the lateral acceleration is greater than a preset third threshold (e.g., 0.6g) and the vehicle speed is greater than a preset fourth threshold (e.g., 40km / h), the target vehicle is determined to have performed a sharp turning operation.

[0032] After identifying multiple high-risk driving operations, this embodiment of the invention identifies the corresponding target driving scenario based on the vehicle safety system status, road images, and external environmental factors at the corresponding time. This determines the specific scenario in which the high-risk driving operation occurred, and further subdivides the high-risk driving operation into high-risk driving behavior events under different scenarios. For example, based on the identified target driving scenario, emergency braking can be subdivided into "emergency braking in urban congestion," "emergency braking on the highway," and "emergency braking (ABS triggered)." It should be noted that, to accurately assess the risk level of driving behavior, this embodiment of the invention considers the specific driving scenario at the time of the high-risk driving operation, assigning different risk coefficients to the same high-risk operation in different driving scenarios. For example, emergency braking on the highway has a higher risk coefficient, while emergency braking in an emergency avoidance scenario has a lower risk coefficient (the driver's subjective responsibility is less). This embodiment of the invention records the number of occurrences, time intervals, corresponding vehicle speeds, and road conditions of various high-risk driving behavior events during each trip, providing data support for subsequent risk assessment.

[0033] As an optional implementation, the driving scene recognition model is trained through the following steps: S201. Obtain vehicle safety system status samples, road image samples, and external environmental factor samples of the test vehicle during the testing phase, and determine the corresponding driving scenario labels through manual annotation. S202. Input the vehicle safety system status sample, road image sample and external environmental factor sample into a pre-built multi-branch fusion neural network to obtain the corresponding predicted driving scenario. S203. Determine the loss value based on the predicted driving scenario and the driving scenario label; S204. Update the parameters of the multi-branch fusion neural network based on the loss value using the backpropagation algorithm to obtain the trained driving scene recognition model. The multi-branch fusion neural network includes a first MLP layer, a CNN layer, a second MLP layer, a feature fusion layer, and an output layer.

[0034] Specifically, the system acquires vehicle safety system status samples, road image samples, and external environmental factor samples during the testing phase. Corresponding driving scenario labels are then manually assigned. These samples are input into a pre-constructed multi-branch fusion neural network to obtain the corresponding predicted driving scenario. A loss value is determined based on the predicted driving scenario and the driving scenario label. The parameters of the multi-branch fusion neural network are updated using a backpropagation algorithm based on the loss value, completing one iteration of training. Training stops when the number of iterations exceeds a preset threshold or the loss value falls below a preset threshold, resulting in a well-trained driving scenario recognition model.

[0035] As a further optional implementation, vehicle safety system state samples, road image samples, and external environmental factor samples are input into a pre-constructed multi-branch fusion neural network to obtain the corresponding predicted driving scenario, which specifically includes: S2021. Input the vehicle safety system state sample into the first MLP layer for feature mapping to obtain the safety system state features; S2022. Input the road image samples into the CNN layer for feature extraction to obtain road condition features; S2023. Input the external environmental factor samples into the second MLP layer for feature mapping to obtain the environmental factor features; S2024. The feature fusion layer performs feature fusion on the safety system state features, road condition features and environmental factor features based on the self-attention mechanism to obtain the fused feature vector. S2025. The fused feature vectors are mapped to the predicted driving scenario through the output layer.

[0036] Specifically, in this embodiment of the invention, the vehicle safety system state samples (whether ABS / ESP is triggered) are encoded into safety system state features through the first MLP layer, the road image samples are encoded into road state features through the CNN layer, the environmental factor samples (temperature, weather) are encoded into environmental factor features through the second MLP layer, and the safety system state features, road condition features and environmental factor features are fused through the feature fusion layer based on the self-attention mechanism to obtain a fused feature vector. Then, it is mapped to a predicted driving scenario through the output layer. The final predicted driving scenario can be an urban congestion scenario, a highway rainy day scenario, an emergency avoidance scenario, etc., which will not be elaborated here.

[0037] After identifying multiple target moments where the target vehicle engages in high-risk driving operations, the vehicle safety system status, road images, and external environmental factors corresponding to the target moments are input into the driving scene recognition model trained through the above steps to obtain the target driving scene corresponding to the target moments.

[0038] As a further optional implementation, high-risk driving behavior events at a target time are determined based on the target driving scenario and the corresponding high-risk driving operation type, specifically including: S1031. Determine the scenario label based on the target driving scenario, and determine the operation type label based on the operation type of the corresponding high-risk driving operation; S1032. Integrate the scene label and operation type label to obtain the high-risk driving behavior label at the target time, and determine the corresponding high-risk driving behavior event based on the high-risk driving behavior label.

[0039] Specifically, scenario labels are determined based on the target driving scenario, such as urban traffic congestion scenarios, highway rainy weather scenarios, and emergency avoidance scenarios. Operation type labels are determined based on the operation type of the corresponding high-risk driving operation, such as rapid acceleration, sudden braking, and sharp turning. Then, the two are integrated to obtain complete high-risk driving behavior labels, thereby identifying the corresponding high-risk driving behavior events, such as "sudden braking in urban traffic congestion," "sudden braking on highways," and "sudden braking for emergency avoidance," etc., which will not be elaborated here.

[0040] As a further optional implementation, the risk level of the target vehicle's driving behavior in the first historical period is assessed based on the distribution of high-risk driving behavior events in the first historical period, specifically including: S1041. Statistically analyze the number of occurrences, minimum time intervals, and maximum severity of each high-risk driving behavior event within the first historical period; S1042. Calculate the event risk score of the corresponding high-risk driving behavior event based on the number of occurrences, minimum time interval, and maximum severity. S1043. Determine the event risk coefficient of each high-risk driving behavior event, and sum the event risk scores of each high-risk driving behavior event according to the event risk coefficient to obtain the total driving behavior risk score of the target vehicle in the first historical period. S1044. Determine the driving behavior risk level based on the total driving behavior risk score.

[0041] Specifically, in this embodiment of the invention, the event risk score Y of each high-risk driving behavior event is calculated based on the number of occurrences S, the minimum time interval T, and the maximum severity N within a first historical period. The specific formula is as follows:

[0042] As can be seen, the event risk score in this embodiment of the invention is positively correlated with the number of occurrences and maximum severity of high-risk driving behavior events, and negatively correlated with the minimum time interval.

[0043] It should be noted that the minimum time interval refers to the minimum time interval between two consecutive high-risk driving behavior events, while the maximum severity refers to the maximum severity of a single high-risk driving behavior event. The severity can be determined based on the acceleration of rapid acceleration, sudden braking, and sharp turns.

[0044] Then, the event risk coefficient of each high-risk driving behavior event is determined. This event risk coefficient can be pre-calibrated manually. For example, the event risk coefficient of "sudden braking in urban congestion" and "sudden braking on highways" can be set to 5, while the event risk coefficient of "sudden braking for emergency avoidance" can be set to 0.5.

[0045] The event risk scores of each high-risk driving behavior event are weighted and summed according to the event risk coefficient to obtain the total driving behavior risk score of the target vehicle in the first historical period. The driving behavior risk level is determined based on the total driving behavior risk score, for example, it can be divided into three levels: high risk, medium risk and low risk.

[0046] As an optional implementation, corresponding driving behavior improvement suggestions are generated, which specifically include: S1045. Based on the event risk score, select several driving behavior events to be optimized from high-risk driving behavior events; S1046. Generate suggestions for improving driving behavior based on the operation type and driving scenario corresponding to the driving behavior event to be optimized.

[0047] Specifically, based on the event risk scores of each high-risk driving behavior event, the priority of each high-risk driving behavior event that requires the driver's attention can be determined. Several high-risk driving behavior events with high event risk scores are selected as driving behavior events to be optimized. Then, corresponding driving behavior improvement suggestions are generated according to their operation type and driving scenario. For example, when there is frequent sudden braking, it can be suggested to "maintain a safe following distance (≥2 seconds in urban areas, ≥3 seconds on highways), observe the road conditions ahead in advance, and avoid following too closely." When there are frequent sharp turns, it can be suggested to "reduce speed to below 30km / h before turning and avoid sharp turns at high speeds." Adaptive suggestions can also be given based on the working conditions and environment in which the behavior occurs. For example, when there is a lot of sudden braking in rainy weather, it can be suggested to "reduce speed by 20% and anticipate braking 50 meters in advance due to slippery road conditions in rainy weather." In addition, the improvement effect can be fed back during the next driving behavior risk assessment. For example, "After adjusting according to the suggestions, the number of sudden brakings has decreased by 30%, continue to maintain this level," forming an improvement loop.

[0048] In some optional embodiments, the present invention can also generate a monthly safety report. The report includes risk level, behavior statistics (number / percentage / time of occurrence of various unsafe behaviors), trend analysis, key risk warnings, and typical behavior cases (such as "all three emergency braking incidents on the highway this month occurred in the rain"). The data is presented intuitively through charts (bar charts to show the number of behaviors and line charts to show the scoring trend). The core information is simplified and displayed on the vehicle's infotainment system, while the detailed report is displayed on the mobile app. The report is automatically generated on the last day of each month and reminders are sent via pop-up windows on the vehicle's infotainment system and push notifications on the mobile app. The report can be exported and shared.

[0049] The method steps of the embodiments of the present invention have been described above. It can be understood that the embodiments of the present invention identify the target time of a high-risk driving operation based on vehicle driving parameters, and then identify the corresponding target driving scenario based on the vehicle safety system status, road image, and external environmental factors at the target time. This allows for the accurate reconstruction of real high-risk driving behavior events based on the target driving scenario and the type of high-risk driving operation. Furthermore, the risk level of the target vehicle's driving behavior is assessed based on the distribution of high-risk driving behavior events. This achieves a comprehensive analysis and assessment of driving behavior and generates targeted suggestions, effectively helping drivers improve driving habits, reduce accident risks, and improve driving safety.

[0050] Reference Figure 2 This invention provides a driving behavior risk assessment device, comprising: The data acquisition module is used to acquire the target vehicle's driving parameters, vehicle safety system status, road images, and external environmental factors during the first historical period. The driving scene recognition module is used to identify multiple target moments when the target vehicle has high-risk driving operations based on vehicle driving parameters, and input the vehicle safety system status, road image and external environmental factors corresponding to the target moment into the pre-trained driving scene recognition model to obtain the target driving scene corresponding to the target moment. The high-risk driving behavior event determination module is used to determine the high-risk driving behavior event at the target time based on the target driving scenario and the operation type of the corresponding high-risk driving operation. The driving behavior risk level assessment module is used to assess the driving behavior risk level of the target vehicle in the first historical period based on the distribution of high-risk driving behavior events in the first historical period, and generate corresponding driving behavior improvement suggestions.

[0051] 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.

[0052] Reference Figure 3 This invention provides an electronic device, comprising: At least one processor; At least one memory for storing at least one program; When the above-mentioned at least one program is executed by the above-mentioned at least one processor, the above-mentioned at least one processor implements the above-mentioned driving behavior risk assessment method.

[0053] 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.

[0054] This invention also provides a computer-readable storage medium storing a processor-executable computer program that, when executed by a processor, implements the aforementioned driving behavior risk assessment method.

[0055] This invention provides a computer-readable storage medium that can execute a driving behavior risk assessment method provided in the method embodiments of this invention. It can execute any combination of the implementation steps of the method embodiments and has the corresponding functions and beneficial effects of the method.

[0056] This invention also provides a computer program product, including a computer program that, when executed by a processor, implements the aforementioned driving behavior risk assessment method.

[0057] It is understood that the content of the above method embodiments is applicable to the embodiments of this program product. The specific functions implemented by the embodiments of this program product 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.

[0058] 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.

[0059] The embodiments described in this invention are for the purpose of more clearly illustrating the technical solutions of the embodiments of this invention, and do not constitute a limitation on the technical solutions provided by the embodiments of this invention. 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 invention are also applicable to similar technical problems.

[0060] The terms "first," "second," "third," "fourth," etc. (if present) in the specification and accompanying drawings of this invention 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 embodiments of the invention 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 a 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.

[0061] In some alternative embodiments, the functions / operations mentioned in the block diagrams may not occur in the order shown in the operation diagrams. For example, depending on the functions / operations involved, two consecutively shown blocks may actually be executed substantially simultaneously, or the aforementioned blocks may sometimes be executed in reverse order. Furthermore, the embodiments presented and described in the flowcharts of this invention are provided by way of example to provide a more comprehensive understanding of the technology. The disclosed methods are not limited to the operations and logic flows presented herein. Alternative embodiments are contemplated in which the order of various operations is changed and sub-operations described as part of a larger operation are executed independently.

[0062] Furthermore, although the invention has been described in the context of functional modules, it should be understood that, unless otherwise stated, one or more of the aforementioned functions and / or features may be integrated into a single physical device and / or software module, or one or more functions and / or features may be implemented in a separate physical device or software module. It is also understood that a detailed discussion of the actual implementation of each module is unnecessary for understanding the invention. Rather, given the properties, functions, and internal relationships of the various functional modules in the apparatus disclosed herein, the actual implementation of the module will be understood within the scope of conventional skill of an engineer. Therefore, those skilled in the art can implement the invention as set forth in the claims using ordinary techniques without excessive experimentation. It is also understood that the specific concepts disclosed are merely illustrative and not intended to limit the scope of the invention, which is determined by the full scope of the appended claims and their equivalents.

[0063] If the aforementioned functions are implemented as software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this invention, or the part that contributes to the prior art, or a portion 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 several 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 described in the various embodiments of this invention. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0064] The logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered as a sequenced list of executable instructions for implementing logical functions, and can be embodied in any computer-readable medium for use by, or in conjunction with, an instruction execution system, apparatus, or device (such as a computer-based system, a processor-including system, or other system that can fetch and execute instructions from, an instruction execution system, apparatus, or device). For the purposes of this specification, "computer-readable medium" can be any means that can contain, store, communicate, propagate, or transmit programs for use by, or in conjunction with, an instruction execution system, apparatus, or device.

[0065] More specific examples (a non-exhaustive list) of computer-readable media include: electrical connections (electronic devices) having one or more wires, portable computer disk drives (magnetic devices), random access memory (RAM), read-only memory (ROM), erasable and editable read-only memory (EPROM or flash memory), fiber optic devices, and portable optical disc read-only memory (CDROM). Furthermore, computer-readable media can even be paper or other suitable media on which the aforementioned program can be printed, because the aforementioned program can be obtained electronically, for example, by optically scanning the paper or other medium, followed by editing, interpreting, or otherwise processing as necessary, and then stored in computer memory.

[0066] It should be understood that various parts of the present invention can be implemented in hardware, software, firmware, or a combination thereof. In the above embodiments, multiple steps or methods can be implemented in software or firmware stored in memory and executed by a suitable instruction execution system. For example, if implemented in hardware, as in another embodiment, it can be implemented using any one or a combination of the following techniques known in the art: discrete logic circuits having logic gates for implementing logical functions on data signals, application-specific integrated circuits (ASICs) having suitable combinational logic gates, programmable gate arrays (PGAs), field-programmable gate arrays (FPGAs), etc.

[0067] In the foregoing description of this specification, references to terms such as "one embodiment," "another embodiment," or "some embodiments" indicate that a specific feature, structure, material, or characteristic described in connection with an embodiment or example is included in at least one embodiment or example of the present invention. In this specification, illustrative expressions of the above terms do not necessarily refer to the same embodiment or example. Furthermore, the specific features, structures, materials, or characteristics described may be combined in any suitable manner in one or more embodiments or examples.

[0068] Although embodiments of the invention have been shown and described, those skilled in the art will understand that various changes, modifications, substitutions and alterations can be made to these embodiments without departing from the principles and spirit of the invention, the scope of which is defined by the claims and their equivalents.

[0069] The above is a detailed description of the preferred embodiments of the present invention. However, the present invention is not limited to the above embodiments. Those skilled in the art can make various equivalent modifications or substitutions without departing from the spirit of the present invention. All such equivalent modifications or substitutions are included within the scope defined by the claims of the present invention.

Claims

1. A method for assessing driving behavior risks, characterized in that, Includes the following steps: Acquire the target vehicle's driving parameters, vehicle safety system status, road images, and external environmental factors during the first historical time period; Based on the vehicle driving parameters, identify multiple target moments when the target vehicle engages in high-risk driving operations, and input the vehicle safety system status, the road image, and the external environmental factors corresponding to the target moments into a pre-trained driving scene recognition model to obtain the target driving scene corresponding to the target moments. The high-risk driving behavior event at the target moment is determined based on the target driving scenario and the corresponding high-risk driving operation type. The risk level of the target vehicle's driving behavior during the first historical period is assessed based on the distribution of the high-risk driving behavior events during the first historical period, and corresponding driving behavior improvement suggestions are generated.

2. The driving behavior risk assessment method according to claim 1, characterized in that, The vehicle driving parameters include vehicle speed, longitudinal acceleration, and lateral acceleration. The high-risk driving operations include rapid acceleration, sudden braking, and sharp turning. The identification of multiple target moments in which the target vehicle engages in high-risk driving operations based on the vehicle driving parameters specifically includes: When the longitudinal acceleration is greater than a preset first threshold, it is determined that the target vehicle is undergoing a rapid acceleration operation, and the corresponding moment is determined as the first target moment; When the longitudinal acceleration is less than a preset second threshold, it is determined that the target vehicle has performed an emergency braking operation, and the corresponding moment is determined as the second target moment; When the lateral acceleration is greater than a preset third threshold and the vehicle speed is greater than a preset fourth threshold, it is determined that the target vehicle is performing a sharp turn, and the corresponding moment is determined as the third target moment.

3. The driving behavior risk assessment method according to claim 1, characterized in that, The driving scene recognition model is trained through the following steps: Acquire vehicle safety system status samples, road image samples, and external environmental factor samples of the test vehicle during the testing phase, and determine the corresponding driving scenario labels through manual annotation; The vehicle safety system state sample, the road image sample, and the external environmental factor sample are input into a pre-constructed multi-branch fusion neural network to obtain the corresponding predicted driving scenario. The loss value is determined based on the predicted driving scenario and the driving scenario label; The parameters of the multi-branch fusion neural network are updated using the backpropagation algorithm based on the loss value to obtain the trained driving scene recognition model. The multi-branch fusion neural network includes a first MLP layer, a CNN layer, a second MLP layer, a feature fusion layer, and an output layer.

4. The driving behavior risk assessment method according to claim 3, characterized in that, The step of inputting the vehicle safety system state sample, the road image sample, and the external environmental factor sample into a pre-constructed multi-branch fusion neural network to obtain the corresponding predicted driving scenario specifically includes: The vehicle safety system state sample is input into the first MLP layer for feature mapping to obtain the safety system state features; The road image samples are input into the CNN layer for feature extraction to obtain road condition features; The external environmental factor samples are input into the second MLP layer for feature mapping to obtain environmental factor features; The feature fusion layer performs feature fusion on the safety system state features, road condition features, and environmental factor features based on a self-attention mechanism to obtain a fused feature vector. The output layer maps the fused feature vector to the predicted driving scenario.

5. The driving behavior risk assessment method according to claim 1, characterized in that, The step of determining the high-risk driving behavior event at the target moment based on the target driving scenario and the corresponding high-risk driving operation type specifically includes: Determine scene labels based on the target driving scenario, and determine operation type labels based on the operation type of the corresponding high-risk driving operation; The scene label and the operation type label are integrated to obtain the high-risk driving behavior label at the target time, and the corresponding high-risk driving behavior event is determined based on the high-risk driving behavior label.

6. A method for assessing driving behavior risk according to any one of claims 1 to 5, characterized in that, The step of assessing the driving behavior risk level of the target vehicle during the first historical period based on the distribution of the high-risk driving behavior events during the first historical period specifically includes: The number of occurrences, minimum time intervals, and maximum severity of each high-risk driving behavior event within the first historical period were statistically analyzed. The event risk score of the high-risk driving behavior event is calculated based on the number of occurrences, the minimum time interval, and the maximum severity. Determine the event risk coefficient of each of the high-risk driving behavior events, and perform a weighted summation of the event risk scores of each of the high-risk driving behavior events based on the event risk coefficients to obtain the total driving behavior risk score of the target vehicle in the first historical period. The driving behavior risk level is determined based on the overall driving behavior risk score.

7. The driving behavior risk assessment method according to claim 6, characterized in that, The generation of corresponding driving behavior improvement suggestions specifically includes: Based on the event risk score, several driving behavior events to be optimized are selected from the high-risk driving behavior events; The driving behavior improvement suggestions are generated based on the operation type and driving scenario corresponding to the driving behavior event to be optimized.

8. A driving behavior risk assessment device, characterized in that, include: The data acquisition module is used to acquire the target vehicle's driving parameters, vehicle safety system status, road images, and external environmental factors during the first historical period. The driving scene recognition module is used to identify multiple target moments when the target vehicle has high-risk driving operations based on the vehicle driving parameters, and input the vehicle safety system status, the road image and the external environmental factors corresponding to the target moments into a pre-trained driving scene recognition model to obtain the target driving scene corresponding to the target moments. The high-risk driving behavior event determination module is used to determine the high-risk driving behavior event at the target moment based on the target driving scenario and the operation type of the corresponding high-risk driving operation. The driving behavior risk level assessment module is used to assess the driving behavior risk level of the target vehicle in the first historical period based on the distribution of the high-risk driving behavior events in the first historical period, and generate corresponding driving behavior improvement suggestions.

9. An electronic device, characterized in that, include: At least one processor; At least one memory for storing at least one program; When the at least one program is executed by the at least one processor, the at least one processor implements a driving behavior risk assessment method as described in 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 the processor, it implements a driving behavior risk assessment method as described in any one of claims 1 to 7.

Images