Data recording method, apparatus and vehicle

Abstract

A data recording method, an apparatus and a vehicle. The data recording method comprises: acquiring first data acquired by a sensing system of a vehicle (S610); storing the first data in a first storage area associated with the vehicle, the first data being data at a first risk level, and the first storage area being associated with the first risk level (S620); acquiring second data acquired by the sensing system of the vehicle (S630); and storing the second data in a second storage area associated with the vehicle, the second data being data at a second risk level, and the second storage area being associated with the second risk level (S640), wherein the first storage area and the second storage area are different storage areas, and the first risk level and the second risk level indicate different degrees of risks of vehicle accidents. The provided data recording method and apparatus are applied to the field of intelligent vehicles, can store data before the occurrence of accidents of vehicles, and / or data that causes risks to the vehicles, so as to reduce the probability of data loss caused by accidents, and ensure the success rate of accident evidence collection, thereby reducing property loss to users.

Description

Data recording methods, devices and vehicles Technical Field

[0001] This application relates to the field of intelligent vehicles, and more specifically, to a data recording method, apparatus, and vehicle. Background Technology

[0002] Information recorded by a vehicle's dashcam (such as video data) is crucial evidence for determining liability in various accidents. Vehicle users have a widespread need for dashcam recording, which has gradually become an essential feature of vehicles. Modern smart vehicles all come equipped with dashcams, and the vehicle's native recording devices automatically record in dangerous situations. However, this video recording is typically triggered by a typical event. For example, when a collision detection system detects a collision, it sends a collision signal to the dashcam module. Upon receiving the collision signal, the dashcam module acquires video data from a period before and after the current time, saves it as emergency video, and then uploads it to a cloud server.

[0003] However, when an accident is serious and causes damage to the vehicle's hardware, video data is easily lost, increasing the difficulty of accident evidence collection and thus severely reducing the user experience. Summary of the Invention

[0004] This application provides a data recording method, apparatus, and vehicle capable of storing data prior to a vehicle accident and / or data that poses a risk to the vehicle, reducing the probability of data loss due to accidents, ensuring the success rate of accident evidence collection, thereby reducing user property losses and improving the user's driving experience.

[0005] Firstly, a data recording method is provided, which can be executed by a vehicle, or by a chip or circuitry used in the vehicle. Specifically, the method can be executed by the vehicle's computing platform.

[0006] The method includes: acquiring first perception data collected by the vehicle's perception system; storing the first perception data in a first storage area associated with the vehicle, wherein the first perception data is data under a first risk level, and the first storage area is associated with the first risk level; acquiring second perception data collected by the perception system; storing the second perception data in a second storage area associated with the vehicle, wherein the second perception data is data under a second risk level, and the second storage area is associated with the second risk level; wherein the first storage area and the second storage area are different storage areas, and the first risk level and the second risk level indicate different degrees of risk of the vehicle causing an accident.

[0007] It should be noted that the first perception data and the second perception data are data collected by the vehicle's perception system at different time periods. Furthermore, the first perception data and the second perception data may include perception data collected by the same sensor of the vehicle, or they may each include perception data collected by different sensors of the vehicle.

[0008] It should also be noted that the vehicle-associated storage area can be understood as any of the following: the storage area is the area of ​​the vehicle's internal storage device; the storage area is the area of ​​the vehicle's external mobile storage device; or, the storage area is the storage area of ​​the cloud server that communicates with the vehicle.

[0009] More specifically, the first risk level and the second risk level can respectively indicate different degrees of risk of the vehicle being involved in an accident in the future. The first perception data is the data under the first risk level, which can be understood as: determining whether the vehicle is currently or will be in the first risk level through the first perception data, and / or the first perception data is the data collected by the vehicle's perception system when the vehicle is in the first risk level.

[0010] The term "risk of vehicle accident" can be understood as: a vehicle may be involved in an accident in the future, but this accident may not actually occur. The degree of risk of an accident indicates the likelihood of the vehicle experiencing such an accident; the higher the degree, the greater the probability of an accident. The aforementioned accidents can include, but are not limited to, collisions, loss of control (such as loss of control due to obstacle avoidance), and rollovers. It is understood that the risk of a vehicle accident can be caused by other road users (such as other vehicles) around the vehicle. The degree of this risk can also indicate the impact of the behavior of other road users on the vehicle's behavior (such as longitudinal speed, lateral deviation, etc.); the higher the degree, the greater the impact of the behavior of other road users on the vehicle's behavior.

[0011] The above technical solution can determine the storage location of perception data before an accident occurs based on the degree of risk that the vehicle will face in the future. This helps to reduce the probability of data loss when an accident actually occurs, thereby improving the success rate of accident evidence collection.

[0012] In conjunction with the first aspect, in some implementations of the first aspect, the method further includes: determining that the vehicle is at a first risk level based on the first perception data; storing the first perception data in a first storage area associated with the vehicle, including: determining the first storage area corresponding to the first risk level based on risk level information, and storing the first perception data in the first storage area; wherein the risk level information indicates the mapping relationship between the risk level and the storage area.

[0013] In conjunction with the first aspect, in some implementations of the first aspect, the method further includes: caching the first perception data to a third storage area.

[0014] In some implementations, when it is determined that the vehicle is at the first risk level based on the first perception data, the first perception data is stored in the first storage area and cached in the third storage area at the same time; or, when the first perception data is obtained, the first perception data is cached in the third storage area, and further, when it is determined that the vehicle is at the first risk level based on the first perception data, the first perception data cached in the third storage area is stored in the first storage area.

[0015] In the above technical solution, relevant data is backed up in multiple storage areas associated with the vehicle. Since the likelihood of multiple storage areas being damaged and data becoming unreadable during an actual accident is low, this helps to further reduce the risk of data loss and ensures data integrity and reliability. Furthermore, the storage area for backing up the first sensing data and the storage area for storing the second sensing data are the same, which helps reduce the complexity of storage area management.

[0016] In conjunction with the first aspect, in some implementations of the first aspect, the second risk level does not meet the preset conditions, while the first risk level meets the preset conditions, the third storage area and the second storage area are the same storage area, and the preset conditions indicate that the degree of risk of a vehicle accident is higher than or equal to the risk threshold.

[0017] In some implementations, the security level of the first storage area is higher than that of the second storage area. The security level of a storage area refers to its ability to resist mechanical failure. For example, mechanical failure of a storage area can include the inability to read data from the storage area due to external forces such as impacts or collisions. A higher security level means a lower probability of damage to the storage area when the vehicle is subjected to impacts or collisions, and a higher likelihood of being able to read data from the storage area.

[0018] In the above technical solution, when the risk of a vehicle accident is higher than the risk threshold, while the vehicle's perception data is pre-stored in a storage area with high resistance to mechanical damage, the perception data is also backed up in other storage areas, which can reduce the probability of data loss when the accident actually occurs.

[0019] In conjunction with the first aspect, in some implementations of the first aspect, the first storage area is a storage area in a mobile memory connected to the vehicle, and the second storage area is a storage area in a memory inside the vehicle.

[0020] In conjunction with the first aspect, in some implementations of the first aspect, the method further includes: sending first sensing data carrying time information to a cloud server.

[0021] In the above technical solution, when the risk of a vehicle accident exceeds the risk threshold, the relevant data is sent to the cloud server to avoid data loss caused by extreme damage to the vehicle, which would prevent data from being read normally from all storage areas.

[0022] In conjunction with the first aspect, in some implementations of the first aspect, the second sensing data is collected by the sensing system after collecting the first sensing data. The method further includes: during the process of storing the first sensing data in the first storage area, determining that the vehicle is at a second risk level based on the second sensing data; storing the second sensing data in the second storage area associated with the vehicle includes: when the second risk level does not meet the preset conditions, storing the second sensing data in the second storage area and suspending the storage of data in the first storage area.

[0023] In the above technical solution, after the accident risk is eliminated, data is no longer stored in the first storage area to reduce the consumption of storage space in the first storage area.

[0024] In conjunction with the first aspect, in some implementations of the first aspect, the method further includes: receiving a first risk report from a cloud server, the first risk report being generated based on third data stored in a first storage space; controlling a vehicle's prompting device to display the content of the first risk report; wherein the first risk report indicates at least one of the following: the start time and / or end time associated with the third data, the type of risk associated with the third data, information on other traffic participants causing the risk, the location of the vehicle associated with the third data, or the vehicle's vehicle control information.

[0025] In the above technical solution, after the vehicle sends relevant data to the cloud server, it can also receive risk reports from the cloud server and display the risk reports of the relevant data, so that users can be aware of the relevant risks, improve users' trust in the vehicle and the user's driving experience.

[0026] Secondly, a data recording device is provided, which is associated with a storage system and includes an acquisition unit. The storage system includes a first storage area and a second storage area. The first storage area is associated with a first risk level, and the second storage area is associated with a second risk level. The first and second risk levels indicate different degrees of risk of a vehicle accident. The acquisition unit is used to: acquire perception data collected by the vehicle's perception system, the perception data including first perception data and second perception data; the first storage area is used to: store the first perception data, which is data under the first risk level; and the second storage area is used to: store the second perception data, which is data under the second risk level.

[0027] The data recording device, associated with the storage system, can store sensed data collected by the vehicle's sensing system into one or more storage areas within the storage system. More specifically, at least one storage area in the storage system can include at least one of the following: a storage area of ​​the vehicle's internal memory; a storage area of ​​an external mobile memory; or a storage area of ​​a cloud server communicating with the vehicle.

[0028] In conjunction with the second aspect, in some implementations of the second aspect, the device further includes a processing unit for: determining, based on the first sensing data, that the vehicle is at a first risk level; determining, based on the risk level information, a first storage area corresponding to the first risk level, and controlling the first sensing data to be stored in the first storage area; wherein the risk level information indicates the mapping relationship between the risk level and the storage area.

[0029] In conjunction with the second aspect, in some implementations of the second aspect, the storage system also includes a third storage area for caching the first perceived data.

[0030] In conjunction with the second aspect, in some implementations of the second aspect, the second risk level does not meet the preset conditions, while the first risk level meets the preset conditions, the third storage area and the second storage area are the same storage area, and the preset conditions indicate that the degree of risk of a vehicle accident is higher than or equal to the risk threshold.

[0031] In conjunction with the second aspect, in some implementations of the second aspect, the first storage area is a storage area in a mobile memory connected to the vehicle, and the second storage area is a storage area in a memory inside the vehicle.

[0032] In conjunction with the second aspect, in some implementations of the second aspect, the device further includes a transceiver unit for: sending first sensing data carrying time information to a cloud server.

[0033] In conjunction with the second aspect, in some implementations of the second aspect, the second sensing data is collected by the sensing system after collecting the first sensing data. The device also includes a processing unit for: determining, based on the second sensing data, that the vehicle is at a second risk level during the process of storing the first sensing data in the first storage area; and controlling the storage of the second sensing data in the second storage area and suspending the storage of data in the first storage area when the second risk level does not meet preset conditions.

[0034] In conjunction with the second aspect, in some implementations of the second aspect, the acquisition unit is further configured to: receive a first risk report from a cloud server, the first risk report being generated based on a third value stored in a first storage space; the device further includes a processing unit configured to: control a vehicle's prompting device to prompt the content of the first risk report; wherein the first risk report indicates at least one of the following: the start time and / or end time of the third data association, the type of risk associated with the third data, information on other traffic participants causing the risk, the location of the vehicle associated with the third data, or the vehicle's vehicle control information.

[0035] Thirdly, a data recording apparatus is provided, the apparatus comprising: a processor for executing a computer program stored in the memory, such that the apparatus performs the method in any possible implementation of the first aspect described above.

[0036] In conjunction with the third aspect, in some implementations of the third aspect, the device also includes a memory.

[0037] Fourthly, a computer program product is provided, comprising: computer program code, which, when executed on a computer or processor, causes the computer or processor to perform the method in any possible implementation of the first aspect.

[0038] It should be noted that the above computer program code can be stored in whole or in part on a storage medium, which can be packaged together with the processor or packaged separately from the processor.

[0039] Fifthly, a computer-readable storage medium is provided, the computer-readable medium storing instructions that, when executed by a processor, cause the processor to implement the method in any possible implementation of the first aspect.

[0040] In a sixth aspect, a chip is provided that includes circuitry for performing the method in any of the possible implementations of the first aspect described above.

[0041] In a seventh aspect, a vehicle is provided that includes means as in any possible implementation of the second or third aspect, or the vehicle includes a computer-readable storage medium as in any possible implementation of the fifth aspect, or the vehicle includes a chip as in any possible implementation of the sixth aspect, or the vehicle is loaded with a computer program product as in any possible implementation of the fourth aspect.

[0042] In conjunction with the seventh aspect, in some implementations of the seventh aspect, the vehicle is a vehicle in a broad sense, such as a means of transportation (e.g., commercial vehicles, passenger cars, motorcycles, flying cars, trains, etc.), industrial vehicles (e.g., forklifts, trailers, tractors, etc.), engineering vehicles (e.g., excavators, bulldozers, cranes, etc.), agricultural equipment (e.g., lawnmowers, harvesters, etc.), amusement equipment, toy vehicles, etc. In practical implementation, the vehicle can also be a road vehicle, a water vehicle, an air vehicle, industrial equipment, agricultural equipment, or other intelligent driving equipment such as entertainment equipment.

[0043] Eighthly, a data recording and analysis system is provided, comprising an apparatus as described in any possible implementation of the second or third aspect, and a data analysis apparatus, wherein the data analysis apparatus is configured to: determine a risk report corresponding to the third data based on third data from the data recording apparatus, the risk report indicating at least one of the following: the start and / or end time of the association of the third data, the type of risk associated with the third data, information on other traffic participants causing the risk, or, the location of the data recording apparatus associated with the third data, and the speed change of the data recording apparatus during the time period associated with the third data; wherein the third data is one of multiple sets of sensing data transmitted from the data recording apparatus to the data analysis apparatus.

[0044] In conjunction with the eighth aspect, in some implementations of the eighth aspect, the data recording device is located in a vehicle, which is associated with at least one electronic device; the data analysis device is also used to: send a risk report to at least one electronic device.

[0045] For the beneficial effects not described in detail in aspects two through eight, please refer to the description in aspect one, which will not be repeated here. Attached Figure Description

[0046] Figure 1 is a schematic block diagram of the data recording system provided in an embodiment of this application;

[0047] Figure 2 is another schematic block diagram of the data recording system provided in an embodiment of this application;

[0048] Figure 3 is a schematic flowchart of the data recording method provided in an embodiment of this application;

[0049] Figure 4 is a schematic diagram of the application scenarios involved in the embodiments of this application;

[0050] Figure 5 is a schematic flowchart of the data analysis method provided in the embodiments of this application;

[0051] Figure 6 is another schematic flowchart of the data recording method provided in the embodiments of this application;

[0052] Figure 7 is a schematic block diagram of the device provided in an embodiment of this application;

[0053] Figure 8 is another schematic block diagram of the device provided in the embodiments of this application. Detailed Implementation

[0054] The technical solutions in this application will now be described with reference to the accompanying drawings.

[0055] Figure 1 is a schematic block diagram of a data recording system provided in an embodiment of this application. As shown in Figure 1, the system includes a vehicle 100, an electronic device 200, and a server 300. The vehicle 100 may include a sensing system 120, a communication system 130, and a computing platform 150. The sensing system 120 may include several sensors for sensing information about the vehicle's surrounding environment. For example, the sensing system 120 may include a positioning system, which can be a global navigation satellite system (GNSS), such as GPS, BeiDou, or other positioning systems. Alternatively, the sensing system 120 may also include one or more of the following: an inertial measurement unit (IMU), lidar, millimeter-wave radar, ultrasonic radar, and a camera device.

[0056] The communication system 130 may integrate one or more devices, including at least one communication module. The communication system 130 can transmit and receive electromagnetic waves via an antenna, enabling the vehicle 100 to communicate with electronic devices 200, server 300, other vehicles, roadside equipment, etc., based on a vehicle-to-everything (V2X) communication network, such as vehicle-to-vehicle (V2V) communication networks, vehicle-to-infrastructure (V2I) communication networks, and vehicle-to-network (V2N) communication networks. Wireless communication technologies may also include short-range wireless communication technologies, such as Bluetooth (BT), radio frequency identification (RFID), and NearLink. For example, the communication system 130 may include an onboard telematics box (T-box), or it may include other communication modules. In actual implementation, vehicle 100 communicates with server 300, roadside equipment, etc. via T-box. Vehicle 100 can also communicate with other devices (such as electronic devices 200) that have the same wireless short-range communication module via other wireless short-range communication modules.

[0057] Some or all of the functions of vehicle 100 can be controlled by computing platform 150. Computing platform 150 may include processors 152 to 15n. A processor is a circuit with signal processing capabilities. In one implementation, the processor can be a circuit with instruction read and execute capabilities, such as a central processing unit (CPU), microprocessor, graphics processing unit (GPU) (which can be understood as a type of microprocessor), or digital signal processor (DSP). In another implementation, the processor can implement certain functions through the logical relationships of hardware circuits. These logical relationships are fixed or reconfigurable. For example, the processor may be a hardware circuit implemented using an application-specific integrated circuit (ASIC) or a programmable logic device (PLD), such as a field-programmable gate array (FPGA). In reconfigurable hardware circuits, the process of the processor loading a configuration document and configuring the hardware circuit can be understood as the process of the processor loading instructions to implement some or all of the functions of the aforementioned units. Furthermore, the processor can also be a hardware circuit designed for artificial intelligence, which can be understood as an ASIC, such as a neural network processing unit (NPU), tensor processing unit (TPU), deep learning processing unit (DPU), etc. In addition, the computing platform 150 may also include memory for storing instructions, and some or all of the processors 152 to 15n can call the instructions in memory to implement the corresponding functions.

[0058] The electronic devices 200 involved in this application may include various handheld devices, wearable devices, computing devices or other processing devices connected to a wireless modem with wireless communication capabilities, as well as various forms of terminals, mobile stations, user equipment, etc., such as mobile phones, watches, tablets, etc.

[0059] In this application, vehicle 100 can send image information collected by perception system 120 to server 300. Server 300 can process the image information reported by vehicle 100, obtain processing results, and push the relevant processing results to electronic device 200.

[0060] The roles of the perception system 120, communication system 130, computing platform 150, electronic device 200, and server 300 in the vehicle 100 in this application are described in detail below with reference to Figure 2. Figure 2 shows a schematic block diagram of the data recording system architecture provided in an embodiment of this application. As shown in Figure 2, the system includes a perception module 210, a data analysis module 220, a data storage control module 230, a data analysis module 310, and a feedback system 320. Exemplarily, the perception module 210 may include one or more sensors in the perception system 120 shown in Figure 1; the data analysis module 220 and the data storage control module 230 may each include one or more processors in the computing platform 150 shown in Figure 1; the data analysis module 310 and the feedback system 320 may each include one or more processors in the server 300. The roles of each module are as described in items (I) to (V) below.

[0061] (i) The perception module 210 is used to collect perception information around the vehicle. This perception information can indicate the location and type of traffic participants around the vehicle, the location of static obstacles in the vehicle's environment, and the structural information of the road where the vehicle is located (such as road boundaries, lane lines, etc.). The perception module 210 can send the perception information it collects to the data analysis module 220.

[0062] (ii) The data analysis module 220 is used to determine the risk level of the current scene of the vehicle based on the perception information from the perception module 210. More specifically, the data analysis module 220 includes a frame extraction module 221 and a risk prediction module 222.

[0063] For example, the aforementioned perception information may include a video stream collected in real time by the camera device, and the frame extraction module 221 is used to extract several frames of images from the video stream at a certain frame extraction frequency; the risk prediction module 222 is used to process the aforementioned several frames of images to determine the risk level of the scene in which the vehicle is currently located.

[0064] (III) The data storage control module 230 is used to store video data according to the risk level determined by the data analysis module 220. More specifically, the data storage control module 230 includes a Class A data storage module 231, a Class B data storage module 232, and a data backup module 233.

[0065] For example, the Class A data storage module 231 is used to control the data backup module 233 to cache or store the video stream or several frames of images captured by the camera device within time period 1 to storage area A when the risk level of the scene where the vehicle is located is greater than or equal to the risk level threshold. Furthermore, the data backup module 233 sends the several frames of images captured within time period 1 to the server via the communication system 130. The Class B data storage module 232 is used to cache or store the video stream or several frames of images captured by the camera device to storage area B when the risk level of the scene where the vehicle is located is less than the risk level threshold. The start time of time period 1 can be the time when the risk level of the scene where the vehicle is located is determined to be greater than or equal to the risk level threshold, or earlier.

[0066] In some implementations, when the risk level of the scene where the vehicle is located is greater than or equal to the risk level threshold, after storing several frames of images collected within time period 1 in storage area A, several frames of images collected within time period 1 can be stored in storage area B.

[0067] In one example, storage area A and storage area B can be different memories. For example, storage area A can be the local memory of vehicle 100, or storage area B can be an external mobile memory of vehicle 100. In yet another example, storage area A and storage area B can also be different locations of the same memory, which can be the local memory of vehicle 100, or the external mobile memory of vehicle 100.

[0068] (iv) The data analysis module 310 is used to analyze the multi-frame images uploaded by the vehicle to obtain a risk report. More specifically, the data analysis module 310 includes a data synthesis module 311 and a risk identification module 312.

[0069] For example, the data synthesis module 311 can synthesize multiple frames of images associated with a certain time period into complete data to be processed, and the risk identification module 312 processes the complete data to be processed to obtain a risk report.

[0070] In some implementations, the aforementioned data analysis module 220 can perform data analysis based on temporal neural network model 1, and the data analysis module 310 can perform data analysis based on temporal neural network model 2. Specifically, both temporal neural network model 1 and temporal neural network model 2 can be neural network models based on attention mechanisms, or both can be neural network models based on the Transformer architecture. The difference is that temporal neural network model 1 can be a lightweight neural network model used to determine the risk level of vehicle driving scenarios, without performing overall scenario analysis, and its computational consumption is less than that of temporal neural network model 2.

[0071] (v) Feedback system 320 is used to push risk reports to the vehicle owner's application (APP) on electronic devices.

[0072] In some implementations, when a vehicle is associated with multiple electronic devices, the feedback system 320 can push risk reports to each of the multiple electronic devices associated with the vehicle.

[0073] The vehicle owner app can be an app that provides vehicle control services to the vehicle owner, and / or an app that provides services such as providing the vehicle owner with information about the vehicle's status. The association between the electronic device and the vehicle can include: the electronic device and the vehicle using the same account; or, although the accounts used to log in to the electronic device and the vehicle are different, both are accounts belonging to an authorized user of the vehicle; or, the electronic device is authorized by an authorized user of the vehicle, thereby establishing a connection between the vehicle and the electronic device.

[0074] It should be understood that the above modules are only an example, and in actual applications, these modules may be added or removed according to actual needs. For example, in the system architecture shown in Figure 2, the data analysis module 220 and the data storage control module 230 can be merged into one module.

[0075] Figure 3 shows a schematic flowchart of a data recording method provided in an embodiment of this application. This method can be executed by the vehicle 100 shown in Figure 1, or by the data analysis module 220 and data storage control module 230 shown in Figure 2. The method 400 includes:

[0076] S401, acquire image data 1 collected by the vehicle's camera device within time period 1, extract n frames of images from image data 1, process the n frames of images, and determine the risk level of the vehicle within time period 1.

[0077] For example, image data 1 can be continuous video stream data; time period 1 can be a value between 5 seconds and 10 seconds, or it can be any other value; n can be an integer between 10 and 20, or it can be any other integer. The end time of time period 1 can be the time when image data 1 is acquired; or, the end time of time period 1 is earlier than the time when image data 1 is acquired, and the time interval between the end time of time period 1 and the time when image data 1 is acquired is less than the duration threshold 1. The duration threshold 1 can be a value between 0.1 seconds and 0.3 seconds, or it can be any other value.

[0078] In some implementations, processing n frames of images to determine the risk level of a vehicle within time period 1 may include steps 1) to 4):

[0079] 1) Data preprocessing: Align the n frames of images to eliminate image shifts caused by vehicle movement or camera shake; use Gaussian filtering, histogram equalization and other techniques to denoise and enhance each frame of the n frames of data.

[0080] Furthermore, an object detection model is used to select the objects to be observed. This object detection model can be a You Only Look Once (YOLO) model, a Fast Region-Based Convolutional Network (Fast R-CNN) model, or other convolutional neural network-based algorithms. For example, the observed objects can be other road users such as motor vehicles, non-motorized vehicles, and pedestrians.

[0081] Furthermore, a multi-target tracking algorithm is used to track the aforementioned observed objects across frames, extracting their features in different images. This multi-target tracking algorithm can be a simple online and real-time tracking (SORT) algorithm, a DeepSORT algorithm, etc.

[0082] 2) Temporal Feature Extraction: Based on the processing results obtained in step 1), temporal-related features such as motion features and position features of the observed object are extracted. Among them, motion features indicate motion-related features such as velocity, acceleration, and direction of motion of the observed object; position features indicate features such as relative distance, relative velocity, and time to collision (TTC) between the observed object and the vehicle.

[0083] 3) Prediction of Observed Object Behavior: The temporal features are input into the time series model to predict at least one of the following: the trajectory of the observed object over a future time period; the relative distance between the vehicle and the observed object over a future time period; or the change in TTC between the vehicle and the observed object over a future time period. The future time period can be any length between 3 and 5 seconds, starting from the end of time period 1. Furthermore, the time series model can be a long short-term memory (LSTM) neural network model, a neural network model based on the Transformer architecture, etc.

[0084] 4) Accident Risk Prediction: Based on the results of the aforementioned observation object behavior prediction, determine the collision risk or probability between the observed object and the self-vehicle. For example, the collision risk or probability can be determined based on the minimum TTC of the observed object and the self-vehicle over a future period. For instance, the relationship between the collision probability and the minimum TTC can satisfy the following formula:

[0085] Where P indicates the collision probability, and its value ranges from 0 to 1, TTC thre The set TTC value, TTC ob This is the minimum TTC mentioned above.

[0086] In some implementations, collision probability can be used to characterize risk levels. For example, based on collision probability, risk levels can be divided into low risk, medium risk, and high risk levels, corresponding to collision probabilities of 0–0.2, 0.2–0.6, and 0.6–1, respectively. In actual implementation, risk levels can also be characterized in other ways, or the risk levels can be divided into more or fewer levels.

[0087] S402, determine whether the risk level is higher than the level threshold.

[0088] For example, the grading threshold can be a medium-risk level.

[0089] Specifically, if the risk level is higher than the risk level threshold, execute S403; otherwise, execute S404.

[0090] S403, cache or store image data 2 in storage area 1, and / or send image data 2 to cloud server.

[0091] In some implementations, image data 2 includes image data 1; or, image data 2 may also include image data acquired before and / or after acquiring image data 1. For example, image data 2 may be in the form of a continuous video stream, or it may be in the form of multiple frames extracted from a video stream.

[0092] In some implementations, when sending image data 2 to the cloud server, each frame of image data 2 carries information about the time it was captured.

[0093] S404, cache or store image data 2 in storage area 2.

[0094] It should be noted that storage area 1 can be storage area A in the aforementioned embodiments, and storage area 2 can be storage area B in the aforementioned embodiments.

[0095] In some implementations, when storage area 1 and storage area 2 are cache areas, the data cache lengths corresponding to storage area 1 and storage area 2 are different. For example, the cache length corresponding to storage area 2 is greater than the cache length corresponding to storage area 1. For example, storage area 1 can be used to store 60 to 120 frames of images, or storage area 1 can be used to store a video stream of 3 to 5 minutes in length, or the data cache length corresponding to the storage area can be other lengths.

[0096] In some implementations, when the risk level is higher than the risk level threshold, image data 2 is cached or stored in storage area 1, and then stored in storage area 2 in an append-only manner.

[0097] It is understandable that "caching" refers to temporary storage, while "storage" in a narrow sense refers to non-volatile storage, i.e., non-temporary storage, sometimes called persistent storage. The concept of "storage" in a broad sense can cover both "caching" and "storage" in a narrow sense. The storage involved in this embodiment can be understood as "storage" in a narrow sense. It should be understood that the above explanation uses collision risk as an example of vehicle risk. In actual implementation, the aforementioned method can also be used to predict the violations or illegal behaviors of other traffic participants. When it is determined that other traffic participants have committed violations or illegal behaviors, it is determined that the vehicle is in a high-risk scenario. For example, taking the scenario shown in Figure 4 as an example, the road where the vehicle is located includes two lanes. The lane line between the lane where the vehicle is located and the lane to the right of its nearest neighbor is a solid line. When the presence of a vehicle in front in the right lane of the vehicle's lane is detected and it is moving towards the destination, it can be determined that the vehicle is in a high-risk scenario, and the real-time perception data (such as images) collected by the vehicle is stored in storage area 1.

[0098] In one example, after determining that the vehicle is in a high-risk scenario, at time 'a' after a certain period of time, a collision occurs between the vehicle and another vehicle, and both vehicles come to a stop. At this point, caching or storing perception data in storage area 1 ceases. It is understandable that even if the collision damages the vehicle's dashcam or other equipment, the data is guaranteed not to be lost because relevant driving data has already been backed up and uploaded before time 'a'.

[0099] In another example, after determining that the vehicle is in a high-risk scenario, at time b after a certain period of time, another vehicle accelerates away from the vehicle, thus eliminating the risk to the vehicle. In this case, the caching or storage of perception data in storage area 1 is stopped.

[0100] In another example, after determining that the vehicle is in a high-risk scenario, at time c after a certain period of time, another vehicle promptly detects the risk, turns back to the correct position, and the risk to the vehicle is eliminated. Then, the vehicle stops caching or storing perception data in storage area 1.

[0101] In some implementations, the recording duration for caching or storing data in storage area 1 when a risk is triggered can be preset. After determining that the risk level is higher than the level threshold and starting to cache or store perception data in storage area 1, the perception data collected by the vehicle's perception system will be cached or stored in storage area 1 regardless of whether the risk is resolved, until the preset recording duration is reached, and then the caching or storage of perception data in storage area 1 will stop.

[0102] The data recording method provided in this application can store data before a vehicle accident occurs, and / or data that may lead to risks to the vehicle, reducing the probability of data loss due to accidents, ensuring the success rate of accident evidence collection, thereby reducing user property losses and improving user driving experience.

[0103] Figure 5 shows a schematic flowchart of a data analysis method provided in an embodiment of this application. This method can be executed by the server 300 shown in Figure 1, or by the data analysis module 310 shown in Figure 2. The method 500 includes:

[0104] S501, Obtain all image data reported by vehicle 1 that are associated with time period 2.

[0105] Understandably, the cloud server can receive image data from multiple vehicles, and each vehicle can report one or more segments of image data.

[0106] S502, perform the first processing on all image data associated with time period 2 to obtain a complete image data segment.

[0107] For example, the first process can be to concatenate all the image data associated with time period 2 in chronological order to obtain a complete image data segment. This image data segment can be regarded as a video stream.

[0108] S503, perform a second processing on the image data segment to obtain the risk report corresponding to time period 2.

[0109] For example, the second processing is used to determine, in the image data segment associated with time period 2, other traffic participants that could cause an accident to vehicle 1 or cause an accident to vehicle 1, as well as the specific type of accident or accident risk.

[0110] For example, each frame of the image data segment can be preprocessed, the observed object determined, and the observed object tracked across frames. Furthermore, based on the results of the cross-frame tracking of the observed object, typical driving events can be identified. Typical driving events may include, but are not limited to: crossing solid lines, sudden braking, changing lanes without using turn signals, or changing lanes without suitable conditions.

[0111] In some implementations, when the object of observation is a vehicle, information such as the license plate number of the object of observation is determined at the same time as the object of observation.

[0112] Furthermore, a risk report is generated based on the information of the observed object, typical driving events, and time period 2. This risk report includes at least one of the following: the start and / or end time of time period 2, the type of risk in time period 2, information on other traffic participants who caused the risk (such as the license plate number of the observed object), the location of the vehicle in time period 2, or the vehicle's vehicle control information. The vehicle control information may include longitudinal vehicle control information and / or lateral vehicle control information. More specifically, longitudinal vehicle control information may include, but is not limited to: speed, acceleration, and gear position; lateral vehicle control information may include, but is not limited to: steering wheel angle and wheel angle.

[0113] The lateral and longitudinal directions involved in this application can be determined relative to the vehicle's driving direction or the vehicle's coordinate system. For example, the longitudinal direction can be parallel to the vehicle's driving direction, and the lateral direction can be perpendicular to the vehicle's driving direction; another example is that the longitudinal direction can be parallel to the X-axis of the vehicle's coordinate system, and the lateral direction can be parallel to the Y-axis of the vehicle's coordinate system. It should be noted that the origin O of the vehicle coordinate system can be located at the projection point of the rear axle center of the vehicle body onto the ground, and the positive directions of the X and Z axes can be the direction of the vehicle's front end and the direction perpendicular to the vehicle's plane, respectively.

[0114] In practice, the image data segment can be input into a large language model (LLM) for secondary processing, or other algorithm models can be used to process the image data segment to obtain a risk report.

[0115] S504, pushes a risk report to one or more electronic devices associated with vehicle 1.

[0116] In some implementations, the risk report can also be pushed to vehicle 1.

[0117] The data analysis method provided in this application can analyze the image data reported by the vehicle to obtain a corresponding risk report and provide feedback to the user, which helps to improve the user's driving experience.

[0118] Figure 6 shows a schematic flowchart of a data recording method provided in an embodiment of this application. This method can be executed by the vehicle 100 shown in Figure 1, or by the data storage control module 230 shown in Figure 2. The method 600 includes:

[0119] S610 acquires the first perception data collected by the vehicle's perception system.

[0120] S620, the first perception data is stored in the first storage area associated with the vehicle. The first perception data is data under the first risk level, and the first storage area is associated with the first risk level.

[0121] S630: Acquire the second sensing data collected by the sensing system.

[0122] S640, the second sense data is stored in a second storage area associated with the vehicle. The second sense data is data under the second risk level, and the second storage area is associated with the second risk level.

[0123] The first storage area and the second storage area are different storage areas, and the first risk level and the second risk level indicate different degrees of risk of vehicle accidents.

[0124] In some implementations, the vehicle is associated with multiple storage areas, including a first storage area and a second storage area, which are used to store perception data under different risk levels.

[0125] In one example, each of the multiple storage areas may correspond to a risk level, used to store perception data collected when the vehicle is at that risk level, and / or to store data determining that the vehicle is at that risk level. For example, if the risk levels are divided into low-risk, medium-risk, and high-risk levels, then the multiple storage areas may include storage areas for perception data collected when the vehicle is at low-risk, medium-risk, and high-risk levels, respectively.

[0126] In another example, a portion of the storage areas in multiple storage regions are used to store perceived data associated with risk levels greater than or equal to the risk level threshold, while the remaining storage areas are used to store perceived data associated with risk levels less than the risk level threshold, or to store perceived data associated with any risk level.

[0127] It should be noted that the "storage" involved in this embodiment should be understood as non-volatile storage.

[0128] In some implementations, the first sensing data and the second sensing data can be data collected by the same sensor, or they can be data collected by different sensors. For example, the first sensing data and the second sensing data can each include images collected by the vehicle's camera device; in other implementations, the first sensing data and the second sensing data can also each include sensing data collected by other sensing systems of the vehicle, such as laser point cloud data, millimeter-wave radar data, etc.

[0129] For example, the first sensing data (or the second sensing data) may include image data in the form of a video stream, or the first sensing data (or the second sensing data) may also include several frames of images extracted from the video stream. More specifically, the first sensing data may include image data 2 in the foregoing embodiments, or may also include other sensing data.

[0130] In some implementations, the first perception data (or second perception data) can be data collected by sensors on the side of the vehicle where the risk exists. For example, if other traffic participants who could cause a vehicle accident are located in front of the vehicle, the first perception data (or second perception data) can be collected by sensors that perceive environmental information in front of the vehicle. For example, the first perception data (or second perception data) can include images collected by the vehicle's forward-facing camera and / or point cloud data collected by a lidar sensor at the front of the vehicle. As another example, if other traffic participants who could cause a vehicle accident are located behind the vehicle, the first perception data (or second perception data) can be collected by sensors that perceive environmental information behind the vehicle. For example, the first perception data (or second perception data) can include images collected by the vehicle's rear-facing camera and / or point cloud data collected by a lidar sensor at the rear of the vehicle.

[0131] It should be clarified that the first perception data and the second perception data are perception data corresponding to different time periods, and respectively record the risk data of the vehicle in the environment in which the vehicle is located during different time periods. For example, the first perception data can be the perception data collected in time period 1 of the aforementioned method 400, and the second perception data can be the perception data collected before or after time period 1 of the aforementioned method 400.

[0132] In some implementations, the method further includes: determining that the vehicle is at a first risk level based on the first perception data; storing the first perception data in a first storage area associated with the vehicle, including: determining the first storage area corresponding to the first risk level based on risk level information, and storing the first perception data in the first storage area; wherein the risk level information indicates the mapping relationship between the risk level and the storage area.

[0133] For example, the risk level information can be the output of the data analysis module 220. In some implementations, the mapping relationship between risk levels and storage areas includes a one-to-one correspondence, that is, the perceived data under a risk level is stored in only one storage area; or, the mapping relationship between risk levels and storage areas also includes: one risk level corresponds to multiple storage areas, that is, the perceived data under a risk level can be stored in multiple storage areas; or, the mapping relationship between risk levels and storage areas also includes: multiple risk levels correspond to one storage area, that is, the perceived data under multiple risk levels can be stored in one storage area.

[0134] For example, the degree of risk of a vehicle accident can be determined based on information such as collision probability and collision time; alternatively, other methods can also be used to determine the degree of risk of a vehicle accident. More specific determination methods can be found in the description of method 400, and will not be repeated here.

[0135] In some implementations, the method also includes caching the first sensing data in a third storage area.

[0136] In some implementations, the second risk level does not meet the preset conditions, while the first risk level does meet the preset conditions. The third storage area and the second storage area are the same storage area. The preset conditions indicate that the risk of a vehicle accident is higher than or equal to a risk threshold. For example, in this implementation, the first storage area can be storage area A in the aforementioned embodiments, and the second storage area can be storage area B in the aforementioned embodiments. That is, the first storage area and the second storage area can be areas used for caching data, or they can be areas used for persistently storing data.

[0137] In this implementation, the security level of the first storage area is higher than that of the second storage area. For example, the first storage area is a storage area in a mobile storage device connected to the vehicle, and the second storage area is a storage area in a storage device inside the vehicle.

[0138] In practical implementation, the level of risk can be represented in various ways. In one example, when the risk level is represented by collision probability, the first risk level can satisfy the preset condition that the collision probability is greater than or equal to a probability threshold, where the probability threshold can be a value between 0.5 and 0.6, or it can be any other value. In another example, when the first risk level is represented by predefined levels, the first risk level can satisfy the preset condition that the risk level is greater than or equal to a level threshold. In other implementations, the level of risk can also be represented in other ways.

[0139] In some implementations, when the first risk level meets the preset conditions, the method further includes: sending first sensing data carrying time information to the cloud server.

[0140] In some implementations, the second perception data is collected by the perception system after collecting the first perception data. The method further includes: determining that the vehicle is at a second risk level based on the second perception data during the process of storing the first perception data in the first storage area; storing the second perception data in the second storage area associated with the vehicle includes: storing the second perception data in the second storage area and suspending the storage of data in the first storage area when the second risk level does not meet the preset conditions.

[0141] For example, the method for determining whether the second risk level meets the preset conditions can be referred to the description in the foregoing embodiments, and will not be repeated here.

[0142] In some implementations, the method further includes: receiving a first risk report from a cloud server, the first risk report being generated based on third data stored in a first storage space; and controlling a vehicle's prompting device to display the content of the first risk report; wherein the first risk report indicates at least one of the following: the start time and / or end time associated with the third data, the type of risk associated with the third data, information on other traffic participants causing the risk, the location of the vehicle associated with the third data, or the vehicle's vehicle control information.

[0143] For example, the third data can be the data associated with time period 2 in method 500, and the start time and / or end time associated with the third data can be the start time and / or end time of the aforementioned time period 2. A more detailed method for determining the risk report can be found in the description of method 500 above, and will not be repeated here.

[0144] The data recording method provided in this application can store data before a vehicle accident occurs, and / or data that may lead to risks to the vehicle, reducing the probability of data loss due to accidents, ensuring the success rate of accident evidence collection, thereby reducing user property losses and improving user driving experience.

[0145] In the various embodiments of this application, unless otherwise specified or in case of logical conflict, the terminology and / or descriptions between the various embodiments are consistent and can be referenced by each other. Technical features in different embodiments can be combined to form new embodiments according to their inherent logical relationships.

[0146] The methods provided by the embodiments of this application have been described in detail above with reference to Figures 1 to 6. The apparatus provided by the embodiments of this application will now be described in detail below with reference to Figures 7 and 8. It should be understood that the descriptions of the apparatus embodiments correspond to the descriptions of the method embodiments; therefore, any content not described in detail can be found in the method embodiments above, and for the sake of brevity, will not be repeated here.

[0147] Figure 7 shows a schematic block diagram of an apparatus 2000 provided in an embodiment of this application. The apparatus 2000 may include units for executing the embodiments described in the foregoing method. Furthermore, each unit in the apparatus 2000 implements a corresponding process of the above-described method embodiments. The apparatus 2000 includes an acquisition unit 2010, which can be used to implement corresponding data acquisition or transmission / reception functions. In some implementations, the apparatus 2000 further includes a processing unit 2020, which can be used to implement corresponding processing functions.

[0148] In addition, the device 2000 is associated with a storage system including a first storage area and a second storage area. The first storage area is associated with a first risk level, and the second storage area is associated with a second risk level. The first risk level and the second risk level indicate different degrees of risk of a vehicle accident.

[0149] The device and storage system are associated with the following: the data recording device can store the sensed data collected by the vehicle's sensing system into one or more storage areas of the storage system. More specifically, at least one storage area in the storage system may include at least one of the following: a storage area of ​​the vehicle's internal memory; a storage area of ​​a mobile memory external to the vehicle; or a storage area of ​​a cloud server communicating with the vehicle.

[0150] The association between the first storage area and the first risk level can be understood as follows: the first storage area is used to store perception data under the first risk level. The first perception data is data under the first risk level, which can be understood as: determining whether the vehicle is currently or in the future under the first risk level through the first perception data, and / or the first perception data is data collected by the vehicle's perception system when the vehicle is under the first risk level.

[0151] Optionally, the apparatus 2000 may further include a storage unit, which can be used to store instructions and / or data, and the processing unit 2020 can read the instructions and / or data in the storage unit so that the apparatus can perform the relevant actions in the foregoing method embodiments.

[0152] It should be understood that the specific process of each unit performing the above-mentioned corresponding steps has been described in detail in the above method embodiments, and will not be repeated here for the sake of brevity.

[0153] It should also be understood that the device 2000 described herein is embodied in the form of a functional unit. The terms “module” or “unit” may refer to application-specific ASICs, electronic circuits, processors (e.g., shared processors, proprietary processors, or group processors) and memory for executing one or more software or firmware programs, integrated logic circuits, and / or other suitable components that support the described functions.

[0154] The apparatuses of the above-described solutions are capable of implementing the corresponding steps in the above-described methods. These functions can be implemented in hardware or by hardware executing corresponding software. The hardware or software includes one or more modules corresponding to the above functions; for example, the acquisition unit 2010 can be replaced by a transceiver, and other units, such as the processing unit, can be replaced by a processor, used to execute the relevant processing operations in each method embodiment.

[0155] In some implementations, when the device 2000 is used to execute method 400 and / or method 600, the acquisition unit 2010 and processing unit 2020 can be located in the vehicle 100 shown in FIG. 1. More specifically, the acquisition unit 2010 and processing unit 2020 can be located in the data storage control module 230, or they can also be located in the data analysis module 220. When the device 2000 is used to execute method 500, the acquisition unit 2010 and processing unit 2020 can be located in the server 300 shown in FIG. 1. More specifically, the acquisition unit 2010 and processing unit 2020 can be located in the data analysis module 310. Exemplarily, the operations performed by the acquisition unit 2010 and processing unit 2020 can be executed by a single processor, or they can be executed by different processors.

[0156] In the specific implementation process, the units in the above device can be fully or partially integrated together, or they can be implemented independently. In one implementation, these units are integrated together and implemented in the form of a system-on-a-chip (SoC).

[0157] Figure 8 is another schematic block diagram of the apparatus provided in an embodiment of this application. The apparatus 2100 shown in Figure 8 may include a processor 2110, a transceiver 2120, and a memory 2130. The processor 2110, transceiver 2120, and memory 2130 are connected via internal interconnection paths. The memory 2130 is used to store instructions, and the processor 2110 is used to execute the instructions stored in the memory 2130 to implement the methods in the above embodiments. Optionally, the memory 2130 may be coupled to the processor 2110 via an interface or integrated with the processor 2110.

[0158] It should be noted that the transceiver 2120 mentioned above may include, but is not limited to, transceiver devices such as input / output interfaces, to realize communication between device 2100 and other devices or communication networks.

[0159] Memory 2130 can be volatile memory and / or non-volatile memory. Non-volatile memory can be read-only memory (ROM), programmable read-only memory (PROM), erasable programmable read-only memory (EPROM), electrically erasable programmable read-only memory (EEPROM), or flash memory. Volatile memory can be random access memory (RAM). For example, RAM can be used as an external cache. By way of example and not limitation, RAM includes various forms such as: static random access memory (SRAM), dynamic random access memory (DRAM), synchronous dynamic random access memory (SDRAM), double data rate synchronous dynamic random access memory (DDR SDRAM), enhanced synchronous dynamic random access memory (ESDRAM), synchronous linked dynamic random access memory (SLDRAM), and direct rambus RAM (DR RAM).

[0160] Transceiver 2120 uses transceiver devices, such as but not limited to transceivers, to enable communication between device 2100 and other devices or communication networks to receive / send data / information for implementing the methods in the above embodiments.

[0161] This application also provides an intelligent driving device, which includes the device 2000 or device 2100 in the above embodiments.

[0162] This application embodiment also provides a data recording and analysis system, which includes a data recording device and a data analysis device. The data recording device is used to record perceived data when the risk level meets preset conditions. The data analysis device is used to: determine a risk report corresponding to the third data based on the third data from the data recording device. The risk report indicates at least one of the following: the start time and / or end time associated with the third data, the type of risk associated with the third data, information on other traffic participants causing the risk, or the location of the data recording device associated with the third data, and the speed change of the data recording device during the time period associated with the third data. The third data is one of multiple sets of perceived data, which are transmitted from the data recording device to the data analysis device.

[0163] This application also provides a computer program product, which includes computer program code. When the computer program code is run on a computer, it causes the computer to implement the methods described in the above embodiments of this application.

[0164] This application also provides a computer-readable storage medium storing computer instructions that, when executed on a computer, cause the computer to implement the methods described in the above embodiments of this application.

[0165] This application also provides a chip, including circuitry, for performing the methods described in the above embodiments of this application.

[0166] Those skilled in the art will understand that, for the sake of convenience and brevity, the specific working processes of the systems, devices, and units described above can be referred to the corresponding processes in the foregoing method embodiments, and will not be repeated here.

[0167] In the description of the embodiments of this application, unless otherwise stated, " / " means "or", for example, A / B can mean A or B; "and / or" in this document describes the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can represent: A existing alone, A and B existing simultaneously, and B existing alone. In this application, "at least one" means one or more, and "more" means two or more. "At least one of the following" or similar expressions refer to any combination of these items, including any combination of single or multiple items. For example, at least one of a, b, or c can represent: a, b, c, ab, ac, bc, or abc, where a, b, and c can be single or multiple.

[0168] The use of prefixes such as "first" and "second" in this application embodiment is solely for distinguishing different descriptive objects and does not limit the position, order, priority, quantity, or content of the described objects. The use of ordinal numbers and other prefixes to distinguish descriptive objects in this application embodiment does not constitute a limitation on the described objects. The description of the described objects is found in the claims or the context of the embodiments, and the use of such prefixes should not constitute unnecessary restrictions.

[0169] In the several embodiments provided in this application, it should be understood that the disclosed systems, apparatuses, and methods can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative; for instance, the division of units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be through some interfaces; the indirect coupling or communication connection between apparatuses or units may be electrical, mechanical, or other forms.

[0170] In the various embodiments of this application, unless otherwise specified or in case of logical conflict, the terminology and / or descriptions between the various embodiments are consistent and can be referenced by each other. Technical features in different embodiments can be combined to form new embodiments according to their inherent logical relationships.

[0171] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0172] In addition, the functional units in the various embodiments of this application can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit.

[0173] The above description is merely a specific embodiment of this application, but the scope of protection of this application is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the scope of the technology disclosed in this application should be included within the scope of protection of this application. Therefore, the scope of protection of this application should be determined by the scope of the claims.

Claims

1. A data recording method, characterized in that, include: Acquire the first perception data collected by the vehicle's perception system; The first sensed data is stored in a first storage area associated with the vehicle. The first sensed data is data under a first risk level, and the first storage area is associated with the first risk level. Acquire the second sensing data collected by the sensing system; The second sensed data is stored in a second storage area associated with the vehicle. The second sensed data is data under the second risk level, and the second storage area is associated with the second risk level. The first storage area and the second storage area are different storage areas, and the first risk level and the second risk level indicate different degrees of risk of the vehicle being involved in an accident.

2. The method according to claim 1, characterized in that, The method further includes: Based on the first sensed data, it is determined that the vehicle is at the first risk level; The step of storing the first sensed data in the first storage area associated with the vehicle includes: Based on the risk level information, determine the first storage area corresponding to the first risk level, and store the first sensed data in the first storage area. The risk level information indicates the mapping relationship between risk level and storage area.

3. The method according to claim 2, characterized in that, The method further includes: The first sensed data is cached in the third storage area.

4. The method according to claim 3, characterized in that, The second risk level does not meet the preset conditions, and the first risk level meets the preset conditions. The third storage area and the second storage area are the same storage area. The preset conditions indicate that the degree of risk of the vehicle causing an accident is higher than or equal to the risk threshold.

5. The method according to claim 4, characterized in that, The first storage area is a storage area in a mobile memory connected to the vehicle, and the second storage area is a storage area in a memory inside the vehicle.

6. The method according to claim 4 or 5, characterized in that, The method further includes: The first sensing data carrying time information is sent to the cloud server.

7. The method according to any one of claims 1 to 6, characterized in that, The second sensing data is collected by the sensing system after collecting the first sensing data, and the method further includes: During the process of storing the first sensed data in the first storage area, the vehicle is determined to be at the second risk level based on the second sensed data; The step of storing the second sensed data in the second storage area associated with the vehicle includes: When the second risk level does not meet the preset conditions, the second sensed data is stored in the second storage area, and the storage of data in the first storage area is suspended.

8. The method according to any one of claims 1 to 7, characterized in that, The method further includes: Receive a first risk report from a cloud server, the first risk report being generated based on third data stored in the first storage space; The vehicle's warning device displays the contents of the first risk report; The first risk report indicates at least one of the following: the start and / or end time of the third data association, the type of risk associated with the third data association, information on other traffic participants that caused the risk, the location of the vehicle associated with the third data association, or the vehicle control information of the vehicle.

9. A data recording device, characterized in that, The device is associated with a storage system, and the device includes an acquisition unit, wherein, The storage system includes a first storage area and a second storage area, the first storage area being associated with a first risk level and the second storage area being associated with a second risk level, the first risk level and the second risk level indicating different degrees of risk of vehicle accidents; The acquisition unit is used to: acquire perception data collected by the vehicle's perception system, the perception data including first perception data and second perception data; The first storage area is used to: store the first sensing data, which is data under the first risk level; The second storage area is used to store the second sensing data, which is data under the second risk level.

10. The apparatus according to claim 9, characterized in that, The device further includes a processing unit for: Based on the first sensed data, it is determined that the vehicle is at the first risk level; Based on the risk level information, determine the first storage area corresponding to the first risk level, and control the first sensed data to be stored in the first storage area. The risk level information indicates the mapping relationship between risk level and storage area.

11. The apparatus according to claim 10, characterized in that, The storage system further includes a third storage area for caching the first sensed data.

12. The apparatus according to claim 11, characterized in that, The second risk level does not meet the preset conditions, and the first risk level meets the preset conditions. The third storage area and the second storage area are the same storage area. The preset conditions indicate that the degree of risk of the vehicle causing an accident is higher than or equal to the risk threshold.

13. The apparatus according to claim 12, characterized in that, The first storage area is a storage area in a mobile memory connected to the vehicle, and the second storage area is a storage area in a memory inside the vehicle.

14. The apparatus according to claim 12 or 13, characterized in that, The device further includes a transceiver unit for: The first sensing data carrying time information is sent to the cloud server.

15. The apparatus according to any one of claims 9 to 14, characterized in that, The second sensing data is collected by the sensing system after collecting the first sensing data. The device further includes a processing unit for: During the process of storing the first sensed data in the first storage area, the vehicle is determined to be at the second risk level based on the second sensed data; When the second risk level does not meet the preset conditions, the second sensed data is controlled to be stored in the second storage area, and the storage of data in the first storage area is suspended.

16. The apparatus according to any one of claims 9 to 15, characterized in that, The acquisition unit is also used for: Receive a first risk report from the cloud server, the first risk report being generated based on a third value stored in the first storage space; The device further includes a processing unit for: The vehicle's warning device displays the contents of the first risk report; The first risk report indicates at least one of the following: the start and / or end time of the third data association, the type of risk associated with the third data association, information on other traffic participants that caused the risk, the location of the vehicle associated with the third data association, or the vehicle control information of the vehicle.

17. A data recording device, characterized in that, include: A processor for executing a computer program stored in memory to cause the apparatus to perform the method as described in any one of claims 1 to 8.

18. A computer-readable storage medium, characterized in that, It stores instructions that, when executed by a processor, implement the method as described in any one of claims 1 to 8.

19. A chip, characterized in that, The chip includes circuitry for performing the method as described in any one of claims 1 to 8.

20. A computer program product, characterized in that, The computer program product includes: computer program code, which, when executed by a processor, implements the method as described in any one of claims 1 to 8.

21. A vehicle, characterized in that, Includes the apparatus as claimed in any one of claims 9 to 17, or the computer-readable storage medium as claimed in claim 18, or the chip as claimed in claim 19, or the vehicle is equipped with the computer program product as claimed in claim 20.

22. A data recording and analysis system, characterized in that, Includes a data recording device as described in any one of claims 9 to 17, and a data analysis device, wherein the data analysis device is used for: Based on third data from the data recording device, a risk report corresponding to the third data is determined, the risk report indicating at least one of the following: the start time and / or end time associated with the third data, the type of risk associated with the third data, information on other traffic participants that caused the risk, or, the location of the data recording device associated with the third data, and the speed change of the data recording device during the time period associated with the third data. The third data is one of multiple sets of sensing data, which are transmitted from the data recording device to the data analysis device.

23. The system according to claim 22, characterized in that, The data recording device is located in a vehicle, which is associated with at least one electronic device; The data analysis device is also used to: send the risk report to the at least one electronic device.

Images