Emergency video recording method of automobile data recorder and related device

Abstract

The invention discloses an emergency video recording method of an automobile data recorder and a related device.The method comprises the steps that after the video recording function of the automobile data recorder of a target vehicle is started, video recording is carried out based on a first recording parameter, and a first video is obtained; acquiring first vehicle data corresponding to the target vehicle; determining second vehicle data according to the first video; performing driving risk assessment according to the first vehicle data and the second vehicle data to obtain a target risk index; when the target danger index is greater than or equal to a preset danger index threshold, adjusting the first recording parameter to obtain a second recording parameter; and performing video recording based on the second recording parameter to obtain a second video. By adopting the method and the device, more comprehensive video data can be obtained.

Description

Technical Field

[0001] The present application relates to the technical field of driving recorder control, and in particular to an emergency recording method and related device of a driving recorder. Background Art

[0002] With the continuous development of automobile technology, driving recorders have become an important tool for ensuring driving safety and handling accident disputes. In the daily use of automobiles, driving recorders can be used to record the specific circumstances when a vehicle breaks down, such as scratches with other vehicles, sudden abnormalities during driving, etc. The specific circumstances when these failures occur are crucial for subsequent vehicle diagnosis, accident liability determination, and insurance claims.

[0003] Existing driving recorders can only perform emergency recording under simple collision or manual trigger conditions. For some special situations, there is a lack of effective perception and recording start-up mechanism. As a result, after a vehicle failure, maintenance personnel find it difficult to obtain detailed video information during the period when the failure occurs, thereby increasing the difficulty and time cost of fault diagnosis, which is not conducive to quickly and accurately solving vehicle problems.

[0004] Therefore, how to use the driving recorder to record emergency videos, obtain video data that can be used as a reference for vehicle diagnosis, and comprehensively and accurately detect emergency situations during vehicle driving, so as to improve the efficiency and accuracy of vehicle fault handling has become an urgent problem to be solved. Summary of the invention

[0005] The embodiment of the present application provides an emergency recording method and related device of a driving recorder. By evaluating the driving risk, when an emergency occurs in a target vehicle, emergency recording is performed through the driving recorder, thereby realizing intelligent adjustment of the recording parameters of the driving recorder under different driving risk levels to obtain more comprehensive emergency video data.

[0006] In a first aspect, an embodiment of the present application provides an emergency recording method of a driving recorder, comprising:

[0007] After the video recording function of the driving recorder of the target vehicle is turned on, a video is recorded based on a first recording parameter to obtain a first video; the first recording parameter is a pre-set recording parameter;

[0008] Acquire first vehicle data corresponding to the target vehicle; the first vehicle data is operation data of the target vehicle;

[0009] Determine second vehicle data according to the first video; the second vehicle data is environmental data of the target vehicle when it is running;

[0010] Performing a driving risk assessment based on the first vehicle data and the second vehicle data to obtain a target risk index;

[0011] When the target risk index is greater than or equal to a preset risk index threshold, adjusting the first recording parameter to obtain a second recording parameter;

[0012] Video recording is performed based on the second recording parameter to obtain a second video.

[0013] In a second aspect, an embodiment of the present application provides an emergency video recording device for a driving recorder, wherein the emergency video recording device for the driving recorder comprises: a first recording module, a first data acquisition module, a second data acquisition module, a risk assessment module, a parameter adjustment module, and a second recording module, wherein:

[0014] The first recording module is used to record a video based on a first recording parameter after the video recording function of the driving recorder of the target vehicle is turned on to obtain a first video; the first recording parameter is a pre-set recording parameter;

[0015] The first data acquisition module is used to acquire first vehicle data corresponding to the target vehicle; the first vehicle data is the operating data of the target vehicle;

[0016] The second data acquisition module is used to determine second vehicle data according to the first video; the second vehicle data is the environmental data of the target vehicle when it is running;

[0017] The risk assessment module is used to perform driving risk assessment based on the first vehicle data and the second vehicle data to obtain a target risk index;

[0018] The parameter adjustment module is used to adjust the first recording parameter to obtain a second recording parameter when the target risk index is greater than or equal to a preset risk index threshold;

[0019] The second recording module is used to record a video based on the second recording parameters to obtain a second video.

[0020] In a third aspect, an embodiment of the present application provides an electronic device, comprising: a processor, a memory, a communication interface, and one or more programs, wherein the one or more programs are stored in the memory and configured to be executed by the processor, and the program includes instructions for executing the steps in the first aspect of the embodiment of the present application.

[0021] In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program for electronic data exchange, wherein the computer program enables a computer to execute part or all of the steps described in the first aspect of the embodiment of the present application.

[0022] In a fifth aspect, an embodiment of the present application provides a computer program product, wherein the computer program product includes a non-transitory computer-readable storage medium storing a computer program, and the computer program is operable to cause a computer to execute some or all of the steps described in the first aspect of the embodiment of the present application. The computer program product may be a software installation package.

[0023] It can be seen that the following beneficial effects are achieved by using the embodiments of the present application:

[0024] By implementing the embodiment of the present application, the driving recorder can first record the video based on the initial first recording parameter, and comprehensively and accurately evaluate the driving risk based on the operating data of the target vehicle and the environmental data extracted from the recorded video. When it is detected that the target risk index is greater than or equal to the preset risk index threshold, the recording parameter is intelligently adjusted to obtain the second recording parameter, and the driving recorder is made to record the video based on the second recording parameter. It can be seen that this method can ensure that more comprehensive and detailed video data can be obtained in an emergency, so that the efficiency and accuracy of vehicle fault handling can be improved based on the video data. BRIEF DESCRIPTION OF THE DRAWINGS

[0025] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the background technology, the drawings required for use in the embodiments of the present application or the background technology will be described below.

[0026] Figure 1 It is a flowchart of an emergency recording method of a driving recorder provided in an embodiment of the present application;

[0027] Figure 2 is an application scenario diagram for determining second vehicle data provided by an embodiment of the present application;

[0028] Figure 3 is a flow chart of a method for determining second vehicle data provided by an embodiment of the present application;

[0029] Figure 4 This is an application scenario diagram of an emergency video recording method provided in an embodiment of the present application;

[0030] Figure 5 is a flow chart of a method for determining a second recording parameter provided in an embodiment of the present application;

[0031] Figure 6It is a structural schematic diagram of an emergency video recording system based on a driving recorder provided in an embodiment of the present application;

[0032] Figure 7 It is a structural schematic diagram of another emergency video recording system based on a driving recorder provided in an embodiment of the present application;

[0033] Figure 8 It is a structural schematic diagram of an emergency video recording device of a driving recorder provided in an embodiment of the present application;

[0034] Fig. 9 It is a structural schematic diagram of an electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0035] In order to enable those skilled in the art to better understand the solution of the present application, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0036] The terms "first", "second", etc. in the specification and claims of this application and the above-mentioned drawings are used to distinguish different objects, rather than to describe a specific order. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions. For example, a process, method, system, product or device that includes a series of steps or units is not limited to the listed steps or units, but optionally includes steps or units that are not listed, or optionally includes other steps or units inherent to these processes, methods, products or devices.

[0037] Reference to "embodiments" herein means that a particular feature, structure, or characteristic described in conjunction with the embodiments may be included in at least one embodiment of the present application. The appearance of the phrase in various locations in the specification does not necessarily refer to the same embodiment, nor is it an independent or alternative embodiment that is mutually exclusive with other embodiments. It is explicitly and implicitly understood by those skilled in the art that the embodiments described herein may be combined with other embodiments.

[0038] The following is an explanation of the relevant contents, concepts, meanings, technical issues, technical solutions, beneficial effects, etc. involved in the embodiments of the present application.

[0039] See also Figure 1 , Figure 1 1 is a flow chart of an emergency recording method of a driving recorder provided in an embodiment of the present application, the method includes but is not limited to the following steps:

[0040] S101. After turning on the recording function of the driving recorder of the target vehicle, recording a video based on a first recording parameter to obtain a first video.

[0041] The first recording parameter is a pre-set recording parameter, which includes video resolution, frame rate, encoding format, viewing angle range, etc., and is not limited here. The video recorded by the driving recorder using the first recording parameter can meet the general recording needs of the surrounding environment of the vehicle under normal driving conditions, and can also reduce the storage space occupied to obtain video data with a certain clarity and continuity.

[0042] In a specific embodiment, the user can start the recording function of the driving recorder by operating the start button of the driving recorder or the relevant instructions of the vehicle system. At this time, the driving recorder starts video recording according to the first recording parameters to obtain a first video. The first video records a continuous picture of the vehicle after the recording function is started. By analyzing the first video, the vehicle operating environment information can be obtained and the driving risk can be evaluated.

[0043] In a possible embodiment, the driving recorder captures the scene in front of the vehicle through its built-in camera, and encodes and stores the captured image sequence according to set parameters, and finally generates a first video.

[0044] S102: Acquire first vehicle data corresponding to the target vehicle.

[0045] The first vehicle data is the operating data of the target vehicle, which can fully reflect the real-time status and operating conditions of the target vehicle. The first vehicle data may include power system related data, such as vehicle speed, engine speed, etc., chassis and driving system data, such as steering wheel steering angle, brake system status, etc., and vehicle electronic system data, such as fault codes, vehicle sensor data, etc.

[0046] In a specific embodiment, the first vehicle data can be obtained through the On-Board Diagnostics (OBD) interface, which establishes a communication connection with the vehicle electronic control unit (ECU). The On-Board Diagnostics interface can read the vehicle's operating data from the ECU, including but not limited to engine speed, vehicle speed, throttle opening, coolant temperature, oil pressure, intake volume, fuel pressure, oxygen sensor feedback data, fault code, etc. The operating data can also be obtained from multiple sensors installed on the target vehicle, including but not limited to acceleration sensors, gyroscope sensors, wheel speed sensors, and brake pressure sensors. Based on the above operating data, the first vehicle data is determined, and by analyzing the first vehicle data, the speed of the target vehicle, whether the vehicle is accelerated suddenly, whether the vehicle is braked suddenly, whether the steering operation of the vehicle is abnormal, etc. can be determined.

[0047] The first vehicle data can be combined with the second vehicle data extracted from the first video to accurately assess the driving risk of the target vehicle driven by the user. For example, by analyzing the changing relationship between the engine speed and the vehicle speed, it can be determined whether the vehicle is in a state of rapid acceleration or deceleration. Combined with the environmental information around the vehicle (such as the distance to the vehicle in front), the potential collision risk can be assessed more accurately.

[0048] If the user does not manually turn on the recording function of the target vehicle's dashcam, the first vehicle data can still be independently analyzed to determine the degree of danger during the current vehicle's driving and obtain the current driving danger index. When the danger index exceeds the preset second danger index threshold, it can be determined that the target vehicle is very likely to encounter an emergency. In this case, in order to more comprehensively grasp the actual situation around the vehicle and further determine whether to start emergency recording, the system will automatically trigger the recording function of the dashcam to record video for analysis.

[0049] S103: Determine second vehicle data according to the first video.

[0050] The second vehicle data is the environmental data of the target vehicle when it is running. The first video is a continuous picture of the scene in front of the vehicle recorded by the dashcam according to the first recording parameters after the recording function is turned on. These pictures contain a lot of information about the driving environment of the vehicle. By analyzing the first video, real-time information about the vehicle's surrounding environment can be obtained, and the second vehicle data can be constructed based on this information. LiDAR technology or multi-sensor fusion technology can also be used to obtain the environmental data of the target vehicle when it is running.

[0051] In a specific embodiment, the first video is analyzed frame by frame using an image processing algorithm or computer vision technology to extract feature information related to the target vehicle's surrounding environment, such as pedestrian information in front of the vehicle, traffic sign information, the distance and relative speed between vehicles, the vehicle's driving environment, road conditions, road obstacle information, and ambient lighting conditions, etc. The second vehicle data is obtained by extracting and analyzing the features of the first video, and organizing and summarizing these extracted environmental features.

[0052] In one possible embodiment, characteristic information about the distance and relative speed between vehicles in the first video can be extracted by using target tracking and distance estimation technology in computer vision to detect the position and size of other vehicles in the first video, and calculate the distance and relative speed between the target vehicle and other vehicles through the position change and time interval between consecutive frames. For example, the relative distance between the target vehicle and the front and rear vehicles can be estimated through the pixel position of the vehicle in multiple frames and the recording parameters of the camera of the driving recorder, and the relative speed can be calculated based on the time difference, so as to judge whether the distance between the vehicles is safe and whether there is a risk of rear-end collision or being rear-end collision.

[0053] See also Figure 2 , Figure 2 is an application scenario diagram for determining second vehicle data provided by an embodiment of the present application, such as Figure 2 As shown, vehicle 21 uses target tracking and distance estimation technology in computer vision to determine the position and size of vehicle 22, and further estimates the relative distance between vehicle 21 and vehicle 22. Of course, vehicle 21 can also use laser radar technology to determine the relative distance between vehicle 21 and the vehicles in front and behind, so as to determine whether the distance between vehicles is safe and whether there is a risk of rear-end collision or being rear-end collision.

[0054] In a possible embodiment, characteristic information about the environment of the vehicle driving state in the first video can be extracted. The motion state of the target vehicle and other vehicles in the first video, including acceleration, deceleration, turning and other actions, can be analyzed. By analyzing the changes in the position and posture of the vehicle in the video, the driving state of the vehicle can be inferred. For example, the acceleration can be calculated by the change in the position of the vehicle in the previous and next frames and the time interval to determine whether the vehicle is accelerating or decelerating, and whether it is driving smoothly. The vehicle's light signals, such as the state of the brake lights and turn signals, can also be observed to understand the operating intentions of other vehicles.

[0055] The second vehicle data contains multi-dimensional information about the surrounding environment when the vehicle is driving. By converting this information into quantifiable and analyzable data, it can be used to evaluate the driving environment conditions of the target vehicle and its potential risks.

[0056] Of course, when the vehicle is stationary, the user can also manually start the recording function of the dashcam according to actual needs to identify real-time information about the surrounding environment when the vehicle is stationary. For example, the user may perceive that there are potential risks around, such as heavy traffic at the parking location of the vehicle. By starting the recording function of the dashcam, the environmental data of the vehicle is obtained, and the environmental data is analyzed to further determine whether emergency recording needs to be started. The system will automatically trigger the recording function of the dashcam to record video for analysis.

[0057] Optionally, see Figure 3 , Figure 3 is a flow chart of a method for determining second vehicle data provided by an embodiment of the present application, which may specifically include the following steps:

[0058] S1031, extracting features from the first video to obtain a plurality of target image features; the target image features are used to characterize the features of the target vehicle related to the environment; the plurality of target image features include: pedestrians in front of the vehicle, traffic signs, distances between vehicles, vehicle driving status, and road conditions;

[0059] S1032, performing quantization processing on each of the multiple target image features to obtain multiple image feature data;

[0060] S1033, determining the influence degree of each target image feature among the multiple target image features on the target vehicle, and obtaining multiple influence degree values; wherein the influence degree value of the image feature is determined by evaluating the image feature according to a preset influence degree evaluation rule; the preset influence degree evaluation rule is constructed based on historical vehicle data;

[0061] S1034, filtering the plurality of image feature data respectively according to the plurality of influence degree values ​​to obtain at least one image feature data; each influence degree value corresponds to one image feature data;

[0062] S1035. Determine the second vehicle data according to the at least one image feature data.

[0063] The preset impact assessment rules are constructed based on historical vehicle data and are used to assess the actual impact of different features on vehicle driving in different scenarios. For example, in high-speed driving scenarios, the distance between vehicles may have a higher impact on driving safety, so its corresponding impact value will be relatively large, while in urban roads, the impact values ​​of traffic signs and pedestrians will be relatively large.

[0064] In a specific embodiment, feature extraction can be performed on the first video to obtain multiple target image features, wherein the target image features are used to characterize the characteristics of the target vehicle related to the environment, and the multiple target image features include: pedestrians in front of the vehicle, traffic signs, distances between vehicles, vehicle driving status, road conditions, etc. It should be noted that by analyzing multiple target image features, the danger of the target vehicle's driving can be determined. For example, by identifying pedestrians appearing in the video screen, including information such as the location, number, walking direction, and speed of pedestrians, it can be assessed whether the sudden appearance of pedestrians may cause potential dangers. By identifying whether there are abnormal conditions such as potholes, water accumulation, and ice on the road surface, it can be assessed whether the road condition will affect the vehicle's handling performance and driving stability, and increase the possibility of accidents.

[0065] Furthermore, each of the multiple target image features is quantified to obtain multiple image feature data. For example, the position information of pedestrians can be converted into specific coordinate values ​​through the image coordinate system, and the distance between vehicles can be calculated using the image ratio relationship to obtain the actual distance value. In order to determine the importance of each target image feature to the driving of the target vehicle, each image feature can be evaluated using a preset impact evaluation rule to obtain multiple impact values.

[0066] According to the obtained multiple impact degree values, multiple image feature data are screened respectively. Specifically, each impact degree value corresponds to one image feature data, and image feature data with a larger impact degree value can be screened out, because such data can better reflect the environmental factors that have an important impact on the driving safety of the vehicle. Then, at least one of the screened image feature data is determined as the second vehicle data, which can comprehensively and specifically reflect the environmental conditions when the target vehicle is running, and can better assess the driving danger.

[0067] S104: Perform driving risk assessment based on the first vehicle data and the second vehicle data to obtain a target risk index.

[0068] In the embodiment of the present application, the first vehicle data reflects the operating status of the target vehicle itself, and the second vehicle data represents the surrounding environment conditions when the vehicle is running. By combining the first vehicle data and the second vehicle data and performing a driving risk assessment, the target risk index can be accurately calculated.

[0069] In a specific embodiment, a driving risk assessment model can be constructed based on historical vehicle data, traffic accident cases and professional knowledge in the field of transportation. The risk assessment model can be constructed using a variety of data analysis and machine learning techniques. For example, a regression analysis method can be used to study the linear or nonlinear relationship between data such as vehicle speed and vehicle distance and the degree of driving risk. A neural network model can also be used to automatically extract complex features and patterns in the data through learning from a large amount of historical data, so as to achieve an accurate assessment of driving risk.

[0070] By inputting the first vehicle data and the second vehicle data into the driving risk assessment model, a corresponding target risk index can be obtained, and the target risk index is used to characterize the risk level of the current driving situation. The higher the value, the greater the risk faced during driving. For example, the value range of the target risk index can be set to 0-100. When the target risk index is lower than 30, it can be considered that the driving is in a relatively safe state. When the index exceeds 70, it indicates that the driving risk is high, and it is necessary to start the emergency recording function of the driving recorder and adjust the recording parameters to record possible emergencies.

[0071] Optionally, the above step S104, performing driving risk assessment according to the first vehicle data and the second vehicle data to obtain a target risk index, may specifically include the following steps:

[0072] S1041. Determine an initial weight corresponding to the first vehicle data according to a preset weight configuration table to obtain a first weight, and determine an initial weight corresponding to the second vehicle data to obtain a second weight; the preset weight configuration table is a weight configuration table predefined in different traffic scenarios based on vehicle type and environmental information;

[0073] S1042, performing driving risk assessment according to the first vehicle data and the second vehicle data respectively to obtain a first risk score and a second risk score;

[0074] S1043: fine-tune the first weight and the second weight according to the first risk score and the second risk score to obtain a third weight and a fourth weight;

[0075] S1044. Determine the target risk index according to the first risk score, the second risk score, the third weight, and the fourth weight.

[0076] Among them, the preset weight configuration table is a weight configuration table pre-defined in different traffic scenarios based on vehicle type and environmental information, which is used to allocate the relative importance of each feature in the first vehicle data and the second vehicle data for driving risk assessment. The preset weight configuration table shows that different types of vehicles have different performance and risk points. For example, trucks focus on vehicle distance and speed, and cars focus on road conditions. In terms of the environment, weather and light affect vehicle performance and field of vision. For example, slippery roads in rainy and snowy days require increased relevant weights. In traffic scenarios, such as highways focus on speed and distance, cities focus on signs and pedestrians, and rural areas focus on road conditions and sight. The corresponding weights are determined by comprehensive analysis of multi-source data and experience.

[0077] In a specific embodiment, the initial weight corresponding to the first vehicle data can be determined according to a preset weight configuration table to obtain a first weight, and the initial weight corresponding to the second vehicle data can be determined at the same time to obtain a second weight, wherein the sum of the first weight and the second weight is 1. Driving risk assessment is performed according to the first vehicle data and the second vehicle data respectively to obtain a first risk score and a second risk score, and then the first weight and the second weight can be fine-tuned according to the first risk score and the second risk score to obtain a third weight and a fourth weight, and finally the target risk index can be determined by weighted summing the first risk score, the second risk score, the third weight and the fourth weight.

[0078] Among them, different first vehicle data and second vehicle data features have different degrees of influence on driving risks, so it is necessary to determine corresponding weights for each data feature. For example, in the highway scenario, vehicle speed is a key indicator of the first vehicle data. Since speed has a significant impact on safety when driving at high speeds, its corresponding initial weight in the weight configuration table will be relatively high. On urban roads, traffic sign recognition is an important part of the second vehicle data. Due to the complexity of urban traffic rules, the initial weight corresponding to this part of the data will be assigned a higher value.

[0079] By evaluating the driving risk of the first vehicle data and comprehensively considering the various operating parameters of the vehicle, the first risk score can be obtained. By evaluating the driving risk of the second vehicle data and focusing mainly on the surrounding environmental factors when the vehicle is running, the second risk score can be obtained. The first risk score and the second risk score reflect the degree of risk brought by the vehicle's own operating state and the surrounding environment respectively. At the same time, in order to make the weight more in line with the actual driving situation, the first weight and the second weight need to be fine-tuned according to these two scores to obtain the third weight and the fourth weight.

[0080] Optionally, the above step S1043, fine-tuning the first weight and the second weight according to the first risk score and the second risk score to obtain the third weight and the fourth weight, may specifically include the following steps:

[0081] Determine the difference between the first hazard score and a preset first threshold value to obtain a first difference; determine the difference between the second hazard score and a preset second threshold value to obtain a second difference; determine a target adjustment ratio based on the first difference and the second difference; and fine-tune the first weight and the second weight based on the target adjustment ratio to obtain the third weight and the fourth weight.

[0082] Among them, the preset first threshold is a preset critical value, which is used to characterize the benchmark of the dangerousness of the vehicle's own operating state, and the preset second threshold is a preset critical value, which is used to characterize the benchmark of the dangerousness of environmental factors.

[0083] In a specific embodiment, the difference between the first danger score and the preset first threshold is determined to obtain a first difference, wherein the first difference can represent the degree of deviation between the current vehicle operating state and the preset danger benchmark. Next, the difference between the second danger score and the preset second threshold is determined to obtain a second difference, wherein the second difference can represent the difference between the danger level of the current vehicle surrounding environment and the preset danger benchmark.

[0084] Furthermore, a target adjustment ratio is determined based on the first difference and the second difference, wherein if the first difference is larger, indicating that the degree of danger brought about by the vehicle's own operating state is relatively higher, then in order to highlight the impact of the first vehicle data in the comprehensive evaluation, a larger target adjustment ratio will be determined accordingly to increase the first weight; otherwise, if the first difference is smaller, the target adjustment ratio will be smaller to reduce the first weight and increase the second weight. It should be noted that the first difference is compared with the second difference. If the first difference is greater than the second difference, the target adjustment ratio can be used to increase the first weight and reduce the second weight; otherwise, the target adjustment ratio is used to reduce the first weight and increase the second weight.

[0085] The first weight and the second weight are fine-tuned according to the target adjustment ratio to obtain the third weight and the fourth weight, wherein the sum of the third weight and the fourth weight is 1. The third weight and the fourth weight obtained by dynamic adjustment can accurately reflect the actual proportion of the first vehicle data and the second vehicle data to the degree of danger in the current driving scenario, thereby more accurately calculating the target danger index.

[0086] See also Figure 4 , Figure 4 is an application scenario diagram of an emergency video recording method provided in an embodiment of the present application, such as Figure 4As shown, through the video display area, it can be judged that the target vehicle has a traffic accident on the current driving section. By analyzing the first vehicle data of the target vehicle and the second vehicle data of the surrounding environment of the target vehicle, it can be determined that the danger index is 75, which exceeds the preset danger index threshold of 70. The recording state of the driving recorder can be adjusted to an emergency recording state to record more comprehensive and detailed video materials.

[0087] S105: When the target risk index is greater than or equal to a preset risk index threshold, adjust the first recording parameter to obtain a second recording parameter.

[0088] Among them, the preset danger index threshold is a key value pre-set based on a large amount of historical data, accident analysis and actual driving experience. It is used to determine whether it is necessary to convert daily recording needs into emergency recordings, ensure that the target vehicle has a certain driving risk, and then adjust the recording parameters for emergency recording.

[0089] In the embodiment of the present application, if it is determined that the target danger index is greater than or equal to the preset danger index threshold, the first recording parameter needs to be adjusted to obtain a second recording parameter that is more suitable for the current dangerous scene. The first recording parameter is used as the recording setting of the driving recorder under daily recording needs, which can meet the general recording requirements when the vehicle is driving normally. However, when facing a higher risk situation, these parameters need to be optimized to capture clearer and more comprehensive key information.

[0090] In a specific embodiment, a variety of factors can be comprehensively considered to ensure that the adjusted parameters can effectively improve the video quality and information richness. For example, the video resolution, frame rate, encoding format, viewing angle range and other parameters can be adjusted. Among them, the improvement of video resolution can make the recorded picture clearer, which is helpful to obtain more detailed information in subsequent analysis. The increase in frame rate can more accurately capture the rapidly changing scene, reduce the picture freeze and information loss, and the optimization of the encoding format can better balance the storage space and transmission efficiency while ensuring the video quality. The adjustment of the viewing angle range can ensure that a wider range of surrounding environments are recorded, providing support for a comprehensive understanding of the background of the event.

[0091] By dynamically adjusting the first recording parameters to generate the second recording parameters, when the target vehicle faces potential danger, the driving recorder can record with more optimized parameters, thereby obtaining more comprehensive and detailed video data.

[0092] Optionally, see Figure 5 , Figure 5 is a flow chart of a method for determining a second recording parameter provided in an embodiment of the present application, which may specifically include the following steps:

[0093] S1051, determining a parameter adjustment range according to the target risk index and the preset risk index threshold;

[0094] S1052: Determine parameter information corresponding to different parameter categories in the first recording parameters to obtain multiple parameter information;

[0095] S1053, determining an adjustment coefficient corresponding to each parameter information in the plurality of parameter information according to the parameter adjustment range, to obtain a plurality of parameter adjustment coefficients;

[0096] S1054, adjusting the plurality of parameter information according to the plurality of parameter adjustment coefficients to obtain a plurality of target parameter information;

[0097] S1055: Combine the multiple target parameter information to obtain the second recording parameter.

[0098] In a specific embodiment, the parameter adjustment range is determined according to the target danger index and the preset danger index threshold, that is, the parameter adjustment range is determined according to the difference between the two. For example, if the target danger index is much higher than the preset danger index threshold, it indicates that the current driving scene is highly dangerous. In order to more effectively record possible emergencies, it is necessary to adjust the recording parameters to a greater extent to obtain clearer and more comprehensive video data. On the contrary, if the target danger index is only slightly higher than the preset danger index threshold, the parameter adjustment range is relatively small, and only the main information is recorded.

[0099] The first recording parameters include multiple different parameter categories, each parameter category corresponds to specific parameter information, and the parameter categories may include video resolution, frame rate, encoding format, viewing angle range, etc. By determining the parameter information corresponding to different parameter categories in the first recording parameters, multiple parameter information can be obtained.

[0100] Based on the parameter adjustment range, a corresponding adjustment coefficient is allocated to each parameter information to obtain multiple parameter adjustment coefficients, wherein the adjustment coefficient is a key factor for converting the parameter adjustment range into a specific parameter adjustment amount. Since different parameter categories have different ways and degrees of influence on the recording effect, the adjustment coefficients are determined in different ways. For each parameter information, calculation or mapping is performed according to its corresponding adjustment coefficient to generate corresponding target parameter information, and multiple target parameter information can be obtained. The multiple target parameter information is combined to obtain a second recording parameter, and the second recording parameter is used for more comprehensive and detailed video recording.

[0101] S106: Record a video based on the second recording parameters to obtain a second video.

[0102] In a specific embodiment, the driving recorder will update the internal recording parameters to the second recording parameters, and based on the second recording parameters, collect image information around the vehicle through the camera to obtain a second video. The second video records the complete situation around the vehicle from the start of recording using the second recording parameters, including the vehicle's driving status, changes in the surrounding environment, the dynamics of other traffic participants, and possible emergencies.

[0103] By analyzing the second video, it can be ensured that if an accident occurs, the second video can clearly present the details of the moment of the accident, so as to help analysts determine the cause of the accident, whether it is caused by vehicle operation error, environmental factors or violations of other vehicles, thereby improving the efficiency and accuracy of vehicle fault handling. The second video provides high-quality and valuable information for driving safety and a series of subsequent processing, greatly improving the information recording and service capabilities of the driving recorder in special circumstances.

[0104] See also Figure 6 , Figure 6 is a structural diagram of an emergency video recording system based on a driving recorder provided in an embodiment of the present application, such as Figure 6 As shown, the emergency recording system based on the driving recorder may include a target vehicle 601 and a remote server 602. The target vehicle 601 and the remote server 602 may be directly connected by wired communication or indirectly connected by wireless communication. The remote server 602 may be an independent physical server, a server cluster or a distributed system composed of multiple physical servers, or a cloud server that provides basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communications, middleware services, domain name services, security services, CDN (Content Delivery Network), and big data and artificial intelligence platforms.

[0105] Optionally, after the above step S106, recording a video based on the second recording parameter to obtain the second video, the following steps may also be included:

[0106] If the target vehicle is connected to a remote server for communication, the attribute information of the second video is marked according to the target danger index to obtain a third video; the third video, the first vehicle data and the second vehicle data are packaged to obtain target metadata; the target metadata is sent to the remote server so that the remote server backs up the target metadata.

[0107] In an embodiment of the present application, the target vehicle can be connected to a remote server for communication to process and transmit data. At the same time, in an emergency, the target vehicle can store key information in the remote server for use and analysis.

[0108] In a specific embodiment, after the driving recorder records the second video, since the video is recorded using the second recording parameters when the target danger index is greater than or equal to the preset danger index threshold, it contains important information when the target vehicle is in a dangerous condition. The target danger index is a quantitative indicator that reflects the current degree of driving danger. The attribute information of the second video can be marked according to the target danger index to obtain the third video, that is, the target danger index can be used as an additional attribute of the second video.

[0109] The third video, the first vehicle data, and the second vehicle data are packaged to form target metadata, which contains all-round information from the vehicle's own status to the external environment and the dangerous situation video, providing comprehensive data support for various subsequent application scenarios. For example, when a vehicle has an accident, the target metadata can fully present the vehicle's operating status before the accident, the surrounding environment, and the dangerous situation at the time, providing sufficient basis for the accident responsibility determination.

[0110] By sending the generated target metadata to a remote server for backup operations, these key data are stored in the corresponding storage device. By storing the target metadata on a remote server, centralized management and secure storage of data are achieved, avoiding the risk of data loss due to failure or damage of the vehicle's local storage device. At the same time, the data stored on the remote server can be easily accessed and used by multiple users or organizations. For example, insurance companies can obtain data through remote servers for insurance claim assessment, maintenance personnel can remotely download data for fault diagnosis, and traffic management departments can also view relevant data for traffic law enforcement and accident investigation when necessary.

[0111] See also Figure 7 , Figure 7 is a structural diagram of another emergency video recording system based on a driving recorder provided in an embodiment of the present application, such as Figure 7As shown, the target vehicle, remote server, communication device 1, communication device 2, and communication device 3 can be connected through any one or more of a local area network, a metropolitan area network, and a wide area network. Among them, communication device 1, communication device 2, and communication device 3 can be a smart phone, a tablet computer, a laptop computer, a desktop computer, a smart speaker, a smart watch, a smart car, etc., but are not limited to this. The remote server can be an independent physical server, or a server cluster or distributed system composed of multiple physical servers, or a cloud server that provides cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communications, middleware services, domain name services, security services, content delivery networks (Content Delivery Network, CDN), and basic cloud computing services such as big data and artificial intelligence platforms. The embodiment of the present application does not limit the type of electronic equipment. Among them, after the target vehicle obtains a dangerous situation, it can broadcast an emergency notification to communication device 1, communication device 2, and communication device 3 through a remote server. For example, when the target vehicle travels to a road section where a traffic accident occurs, a video of the road section can be recorded and dangerous situation information can be generated to alert the dangerous situation on the road section. At the same time, corresponding emergency measures can be taken according to the dangerous situation information.

[0112] Optionally, the method may further include the following steps:

[0113] S1061, determining a target danger situation of the target vehicle according to the target metadata;

[0114] S1062, generating first emergency information according to the target dangerous situation; the first emergency information includes: recording time, danger level;

[0115] S1063: When the target dangerous situation is a vehicle failure, determine second emergency information according to the target metadata; the second emergency information includes: a vehicle fault code and vehicle location information;

[0116] S1064. Determine a first emergency notification according to the first emergency information and the second emergency information;

[0117] S1065. When the target dangerous situation is a situation occurring in the surrounding environment of the vehicle, determine third emergency information according to the target metadata; the third emergency information includes: vehicle driving state information and surrounding environment information;

[0118] S1066. Determine a second emergency notification according to the first emergency information and the third emergency information.

[0119] In a specific embodiment, the target dangerous situation of the target vehicle can be determined based on the target metadata. For example, by analyzing the running state of the vehicle in the first vehicle data and the abnormal situation of the vehicle's surrounding environment in the second vehicle data, it can be identified whether the target vehicle is in a fault state of the vehicle itself or the vehicle's surrounding environment has a condition that may affect driving safety, thereby determining the target dangerous situation. The first emergency information is generated based on the target dangerous situation, wherein the first emergency information includes: recording time, danger level, etc.

[0120] When the target dangerous situation is a vehicle failure, the second emergency information can be determined according to the target metadata, wherein the second emergency information includes: a vehicle fault code, vehicle location information, etc. The first emergency notification is determined according to the first emergency information and the second emergency information.

[0121] The first emergency notification integrates important information such as recording time, danger level, vehicle fault code and vehicle location information, and can be sent to relevant personnel or systems in a variety of ways, such as to the vehicle manufacturer's service center, insurance company, car owner's mobile phone application, etc. The first emergency notification can provide detailed information when the vehicle fails, including when the failure occurred, the severity of the failure, the specific location of the failure and the specific code of the failure, so as to take corresponding measures based on the information, such as arranging rescue, repair or claim settlement.

[0122] When the target dangerous situation is a situation in the surrounding environment of the vehicle, the third emergency information can be determined according to the target metadata, wherein the third emergency information includes: vehicle driving state information, surrounding environment information, etc. The second emergency notification is determined according to the first emergency information and the third emergency information.

[0123] The second emergency notification includes important information such as recording time, danger level, vehicle driving status information and surrounding environment information. The second emergency notification can be sent to traffic police, insurance companies, and other nearby vehicles so that corresponding actions can be taken according to the impact of environmental issues on vehicle driving, such as directing traffic, assessing accident risks, or handling subsequent insurance matters.

[0124] In summary, by implementing the embodiment of the present application, after turning on the recording function of the driving recorder of the target vehicle, a video is recorded based on a first recording parameter to obtain a first video; first vehicle data corresponding to the target vehicle is obtained; second vehicle data is determined based on the first video; driving risk assessment is performed based on the first vehicle data and the second vehicle data to obtain a target risk index; when the target risk index is greater than or equal to a preset risk index threshold, the first recording parameter is adjusted to obtain a second recording parameter; and a video is recorded based on the second recording parameter to obtain a second video. It can be seen that this method can ensure that more comprehensive and detailed video data can be obtained in an emergency, so that the efficiency and accuracy of vehicle fault handling can be improved based on the video data.

[0125] See also Figure 8 , Figure 8 800 is a schematic diagram of the structure of an emergency video recording device of a driving recorder provided in an embodiment of the present application. The emergency video recording device 800 of the driving recorder includes: a first recording module 801, a first data acquisition module 802, a second data acquisition module 803, a risk assessment module 804, a parameter adjustment module 805, and a second recording module 806, wherein:

[0126] The first recording module 801 is used to record a video based on a first recording parameter after the video recording function of the driving recorder of the target vehicle is turned on to obtain a first video; the first recording parameter is a pre-set recording parameter;

[0127] The first data acquisition module 802 is used to acquire first vehicle data corresponding to the target vehicle; the first vehicle data is the operating data of the target vehicle;

[0128] The second data acquisition module 803 is used to determine second vehicle data according to the first video; the second vehicle data is the environmental data of the target vehicle when it is running;

[0129] The risk assessment module 804 is used to perform driving risk assessment based on the first vehicle data and the second vehicle data to obtain a target risk index;

[0130] The parameter adjustment module 805 is used to adjust the first recording parameter to obtain a second recording parameter when the target risk index is greater than or equal to a preset risk index threshold;

[0131] The second recording module 806 is used to perform video recording based on the second recording parameters to obtain a second video.

[0132] Optionally, in determining the second vehicle data according to the first video, the second data acquisition module 803 is further specifically configured to:

[0133] Extracting features from the first video to obtain a plurality of target image features; the target image features are used to characterize the features of the target vehicle related to the environment; the plurality of target image features include: pedestrians in front of the vehicle, traffic signs, distances between vehicles, vehicle driving status, and road conditions;

[0134] quantizing each of the plurality of target image features to obtain a plurality of image feature data;

[0135] Determine the degree of influence of each target image feature among the multiple target image features on the target vehicle, and obtain multiple influence degree values; wherein the image feature is evaluated by a preset influence degree evaluation rule to determine the influence degree value of the image feature; the preset influence degree evaluation rule is constructed based on historical vehicle data;

[0136] The plurality of image feature data are screened respectively according to the plurality of influence degree values ​​to obtain at least one image feature data; each influence degree value corresponds to one image feature data;

[0137] The second vehicle data is determined based on the at least one image feature data.

[0138] Optionally, in the aspect of performing driving risk assessment according to the first vehicle data and the second vehicle data to obtain a target risk index, the risk assessment module 804 is further specifically used for:

[0139] Determine the initial weight corresponding to the first vehicle data according to a preset weight configuration table to obtain a first weight, and determine the initial weight corresponding to the second vehicle data to obtain a second weight; the preset weight configuration table is a weight configuration table predefined in different traffic scenarios based on vehicle type and environmental information;

[0140] Performing driving risk assessment according to the first vehicle data and the second vehicle data to obtain a first risk score and a second risk score;

[0141] Fine-tuning the first weight and the second weight according to the first risk score and the second risk score to obtain a third weight and a fourth weight;

[0142] The target risk index is determined according to the first risk score, the second risk score, the third weight and the fourth weight.

[0143] Optionally, in the aspect of fine-tuning the first weight and the second weight according to the first risk score and the second risk score to obtain a third weight and a fourth weight, the risk assessment module 804 is further specifically configured to:

[0144] Determine a difference between the first risk score and a preset first threshold value to obtain a first difference;

[0145] Determine a difference between the second risk score and a preset second threshold value to obtain a second difference;

[0146] determining a target adjustment ratio according to the first difference and the second difference;

[0147] The first weight and the second weight are fine-tuned according to the target adjustment ratio to obtain the third weight and the fourth weight.

[0148] Optionally, in the step of adjusting the first recording parameter according to the target risk index to obtain the second recording parameter, the parameter adjustment module 805 is further specifically configured to:

[0149] Determining a parameter adjustment range according to the target risk index and the preset risk index threshold;

[0150] Determine parameter information corresponding to different parameter categories in the first recording parameters to obtain multiple parameter information;

[0151] Determine an adjustment coefficient corresponding to each parameter information in the plurality of parameter information according to the parameter adjustment range, and obtain a plurality of parameter adjustment coefficients;

[0152] Adjusting the plurality of parameter information according to the plurality of parameter adjustment coefficients to obtain a plurality of target parameter information;

[0153] The multiple target parameter information are combined to obtain the second recording parameter.

[0154] Optionally, after recording the video based on the second recording parameter to obtain the second video, the emergency video recording device 800 of the driving recorder is further specifically used for:

[0155] If the target vehicle is in communication connection with the remote server, the attribute information of the second video is marked according to the target danger index to obtain a third video;

[0156] Packing the third video, the first vehicle data, and the second vehicle data to obtain target metadata;

[0157] The target metadata is sent to the remote server so that the remote server backs up the target metadata.

[0158] Optionally, the emergency video recording device 800 of the driving recorder is further specifically used for:

[0159] determining a target dangerous situation of the target vehicle according to the target metadata;

[0160] Generate first emergency information according to the target dangerous situation; the first emergency information includes: recording time and danger level;

[0161] When the target dangerous situation is a vehicle failure, determining second emergency information according to the target metadata; the second emergency information includes: a vehicle fault code and vehicle location information;

[0162] determining a first emergency notification according to the first emergency information and the second emergency information;

[0163] When the target dangerous situation is a situation occurring in the surrounding environment of the vehicle, third emergency information is determined according to the target metadata; the third emergency information includes: vehicle driving state information and surrounding environment information;

[0164] A second emergency notification is determined according to the first emergency information and the third emergency information.

[0165] The emergency video recording device 800 of the driving recorder described in the present application can, after turning on the video recording function of the driving recorder of the target vehicle, record a video based on a first recording parameter to obtain a first video; obtain first vehicle data corresponding to the target vehicle; determine second vehicle data based on the first video; perform a driving risk assessment based on the first vehicle data and the second vehicle data to obtain a target risk index; when the target risk index is greater than or equal to a preset risk index threshold, adjust the first recording parameter to obtain a second recording parameter; and record a video based on the second recording parameter to obtain a second video. It can be seen that this method can ensure that more comprehensive and detailed video data can be obtained in an emergency, so that the efficiency and accuracy of vehicle fault handling can be improved based on the video data.

[0166] See also Fig. 9 , Fig. 9 : is a structural diagram of an electronic device provided in an embodiment of the present application, the electronic device may include a processor, a memory, a communication interface and one or more programs, the processor, the memory and the communication interface may be interconnected through a bus; the one or more programs are stored in the memory and configured to be executed by the processor; in the embodiment of the present application, the program includes instructions for executing the following steps:

[0167] After the video recording function of the driving recorder of the target vehicle is turned on, a video is recorded based on a first recording parameter to obtain a first video; the first recording parameter is a pre-set recording parameter;

[0168] Acquire first vehicle data corresponding to the target vehicle; the first vehicle data is operation data of the target vehicle;

[0169] Determine second vehicle data according to the first video; the second vehicle data is environmental data of the target vehicle when it is running;

[0170] Performing a driving risk assessment based on the first vehicle data and the second vehicle data to obtain a target risk index;

[0171] When the target risk index is greater than or equal to a preset risk index threshold, adjusting the first recording parameter to obtain a second recording parameter;

[0172] Video recording is performed based on the second recording parameter to obtain a second video.

[0173] The electronic device described in the present application can, after turning on the recording function of the target vehicle's driving recorder, record a video based on a first recording parameter to obtain a first video; obtain first vehicle data corresponding to the target vehicle; determine second vehicle data based on the first video; perform a driving risk assessment based on the first vehicle data and the second vehicle data to obtain a target risk index; when the target risk index is greater than or equal to a preset risk index threshold, adjust the first recording parameter to obtain a second recording parameter; and record a video based on the second recording parameter to obtain a second video. It can be seen that this method can ensure that more comprehensive and detailed video data can be obtained in an emergency, so that the efficiency and accuracy of vehicle fault handling can be improved based on the video data.

[0174] An embodiment of the present application also provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program for electronic data exchange, wherein the computer program enables a computer to execute part or all of the steps of any method recorded in the above method embodiment, and the above computer includes an electronic device.

[0175] The present application also provides a computer program product, which includes a non-transitory computer-readable storage medium storing a computer program, and the computer program is operable to cause a computer to execute some or all of the steps of any method described in the method embodiment. The computer program product may be a software installation package, and the computer includes an electronic device.

[0176] Those skilled in the art can understand that to implement all or part of the processes in the above-mentioned embodiments, the processes can be completed by computer programs to instruct related hardware, and the programs can be stored in computer-readable storage media. When the programs are executed, they can include the processes of the above-mentioned method embodiments. The aforementioned storage media include: ROM or random access memory RAM, magnetic disk or optical disk and other media that can store program codes.

[0177] The steps of the method or algorithm described in the embodiments of the present application can be implemented in hardware or by executing software instructions by a processor. The software instructions can be composed of corresponding software modules, and the software modules can be stored in RAM, flash memory, ROM, EPROM, electrically erasable programmable read-only memory (electrically EPROM, EEPROM), registers, hard disks, mobile hard disks, read-only compact disks (CD-ROMs) or any other form of storage medium known in the art. An exemplary storage medium is coupled to the processor so that the processor can read information from the storage medium and write information to the storage medium. Of course, the storage medium can also be a component of the processor. The processor and the storage medium can be located in an ASIC. In addition, the ASIC can be located in a terminal device or a management device. Of course, the processor and the storage medium can also be present in a terminal device or a management device as discrete components.

[0178] Those skilled in the art should be aware that in one or more of the above examples, the functions described in the embodiments of the present application can be implemented in whole or in part by software, hardware, firmware, or any combination thereof. When implemented using software, it can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on a computer, the process or function described in the embodiments of the present application is generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions can be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another computer-readable storage medium. For example, the computer instructions can be transmitted from a website site, computer, server, or data center to another website site, computer, server, or data center by wired (e.g., coaxial cable, optical fiber, digital subscriber line (digital subscriber line, DSL)) or wireless (e.g., infrared, wireless, microwave, etc.) mode. The computer-readable storage medium can be any available medium that a computer can access or a data storage device such as a server or data center that includes one or more available media integrations. The available medium may be a magnetic medium (eg, a floppy disk, a hard disk, a magnetic tape), an optical medium (eg, a digital video disc (DVD)), or a semiconductor medium (eg, a solid state disk (SSD)).

[0179] The modules / units included in the devices and products described in the above embodiments may be software modules / units or hardware modules / units, or may be partially software modules / units and partially hardware modules / units. For example, for the devices and products applied to or integrated in the chip, the modules / units included therein may all be implemented in the form of hardware such as circuits, or at least some of the modules / units may be implemented in the form of software programs, which run on the processor integrated inside the chip, and the remaining (if any) modules / units may be implemented in the form of hardware such as circuits; for the devices and products applied to or integrated in the chip module, the modules / units included therein may all be implemented in the form of hardware such as circuits, and different modules / units may be located in the same component (such as a chip, circuit module, etc.) or in different components of the chip module, or at least some of the modules / units may be implemented in the form of software programs. The software programs run on the processor integrated inside the chip, and the remaining (if any) modules / units may be implemented in the form of hardware such as circuits. It is implemented in the form of a software program, which runs on a processor integrated inside the chip module, and the remaining (if any) modules / units can be implemented in hardware such as circuits; for various devices and products applied to or integrated in the terminal equipment, the various modules / units contained therein can be implemented in hardware such as circuits, and different modules / units can be located in the same component (for example, chip, circuit module, etc.) or in different components in the terminal equipment, or, at least some modules / units can be implemented in the form of a software program, which runs on a processor integrated inside the terminal equipment, and the remaining (if any) modules / units can be implemented in hardware such as circuits.

[0180] The specific implementation methods described above further illustrate the purpose, technical solutions and beneficial effects of the embodiments of the present application. It should be understood that the above description is only the specific implementation method of the embodiments of the present application and is not intended to limit the protection scope of the embodiments of the present application. Any modifications, equivalent substitutions, improvements, etc. made on the basis of the technical solutions of the embodiments of the present application should be included in the protection scope of the embodiments of the present application.

Claims

1. An emergency recording method of a driving recorder, characterized in that: The method comprises: After the video recording function of the driving recorder of the target vehicle is turned on, a video is recorded based on a first recording parameter to obtain a first video; the first recording parameter is a pre-set recording parameter; Acquire first vehicle data corresponding to the target vehicle; the first vehicle data is operating data of the target vehicle; Determine second vehicle data according to the first video; the second vehicle data is environmental data of the target vehicle when it is running; Performing a driving risk assessment based on the first vehicle data and the second vehicle data to obtain a target risk index; When the target risk index is greater than or equal to a preset risk index threshold, adjusting the first recording parameter to obtain a second recording parameter; Video recording is performed based on the second recording parameter to obtain a second video.

2. The method according to claim 1, characterized in that The determining the second vehicle data according to the first video includes: Extracting features from the first video to obtain a plurality of target image features; the target image features are used to characterize the features of the target vehicle related to the environment; the plurality of target image features include: pedestrians in front of the vehicle, traffic signs, distances between vehicles, vehicle driving status, and road conditions; Quantifying each of the plurality of target image features to obtain a plurality of image feature data; Determine the degree of influence of each target image feature among the multiple target image features on the target vehicle, and obtain multiple influence degree values; wherein the image feature is evaluated by a preset influence degree evaluation rule to determine the influence degree value of the image feature; the preset influence degree evaluation rule is constructed based on historical vehicle data; The plurality of image feature data are screened respectively according to the plurality of influence degree values ​​to obtain at least one image feature data; each influence degree value corresponds to one image feature data; The second vehicle data is determined based on the at least one image feature data.

3. The method according to claim 1 or 2, characterized in that The step of performing driving risk assessment according to the first vehicle data and the second vehicle data to obtain a target risk index includes: Determine the initial weight corresponding to the first vehicle data according to a preset weight configuration table to obtain a first weight, and determine the initial weight corresponding to the second vehicle data to obtain a second weight; the preset weight configuration table is a weight configuration table predefined in different traffic scenarios based on vehicle type and environmental information; Performing driving risk assessment according to the first vehicle data and the second vehicle data to obtain a first risk score and a second risk score; Fine-tuning the first weight and the second weight according to the first risk score and the second risk score to obtain a third weight and a fourth weight; The target risk index is determined according to the first risk score, the second risk score, the third weight and the fourth weight.

4. The method according to claim 3, characterized in that The step of fine-tuning the first weight and the second weight according to the first risk score and the second risk score to obtain a third weight and a fourth weight comprises: Determine a difference between the first risk score and a preset first threshold value to obtain a first difference; Determine a difference between the second risk score and a preset second threshold value to obtain a second difference; determining a target adjustment ratio according to the first difference and the second difference; The first weight and the second weight are fine-tuned according to the target adjustment ratio to obtain the third weight and the fourth weight.

5. The method according to claim 1, characterized in that The adjusting the first recording parameter according to the target risk index to obtain the second recording parameter includes: Determining a parameter adjustment range according to the target risk index and the preset risk index threshold; Determine parameter information corresponding to different parameter categories in the first recording parameters to obtain multiple parameter information; Determine an adjustment coefficient corresponding to each parameter information in the plurality of parameter information according to the parameter adjustment range, and obtain a plurality of parameter adjustment coefficients; Adjusting the plurality of parameter information according to the plurality of parameter adjustment coefficients to obtain a plurality of target parameter information; The multiple target parameter information are combined to obtain the second recording parameter.

6. The method according to any one of claims 1 to 5, characterized in that: After recording the video based on the second recording parameter to obtain the second video, the method further includes: If the target vehicle is in communication connection with the remote server, the attribute information of the second video is marked according to the target danger index to obtain a third video; Packing the third video, the first vehicle data, and the second vehicle data to obtain target metadata; The target metadata is sent to the remote server so that the remote server backs up the target metadata.

7. The method according to claim 6, characterized in that The method further comprises: determining a target dangerous situation of the target vehicle according to the target metadata; Generate first emergency information according to the target dangerous situation; the first emergency information includes: recording time and danger level; When the target dangerous situation is a vehicle failure, determining second emergency information according to the target metadata; the second emergency information includes: a vehicle fault code and vehicle location information; determining a first emergency notification according to the first emergency information and the second emergency information; When the target dangerous situation is a situation occurring in the surrounding environment of the vehicle, third emergency information is determined according to the target metadata; the third emergency information includes: vehicle driving state information and surrounding environment information; A second emergency notification is determined according to the first emergency information and the third emergency information.

8. An emergency video recording device for a driving recorder, characterized in that: The emergency video recording device of the driving recorder includes: a first recording module, a first data acquisition module, a second data acquisition module, a risk assessment module, a parameter adjustment module, and a second recording module, wherein: The first recording module is used to record a video based on a first recording parameter after the video recording function of the driving recorder of the target vehicle is turned on to obtain a first video; the first recording parameter is a pre-set recording parameter; The first data acquisition module is used to acquire first vehicle data corresponding to the target vehicle; the first vehicle data is the operating data of the target vehicle; The second data acquisition module is used to determine second vehicle data according to the first video; the second vehicle data is the environmental data of the target vehicle when it is running; The risk assessment module is used to perform driving risk assessment based on the first vehicle data and the second vehicle data to obtain a target risk index; The parameter adjustment module is used to adjust the first recording parameter to obtain a second recording parameter when the target risk index is greater than or equal to a preset risk index threshold; The second recording module is used to record a video based on the second recording parameters to obtain a second video.

9. An electronic device, characterized in that: include: A processor, a memory, a communication interface, and one or more programs; The one or more programs are stored in the memory and configured to be executed by the processor, the programs comprising instructions for executing the steps in the method according to any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, wherein the computer program includes program instructions, and when the program instructions are executed by a processor, the processor is caused to perform the method according to any one of claims 1 to 7.

Images