Data recording method, device, equipment and storage medium of event data recorder

Abstract

The application discloses an event data recorder data recording method, device, equipment and storage medium, relates to the technical field of data recording, and discloses an event data recorder data recording method, which comprises the following steps: acquiring a data recording group number, an initial weight and a weight attenuation gradient; weighting event frame data according to the initial weight to obtain initial event frame data, storing the initial event frame data into a data recording group to obtain an initial data recording group; deleting target event frame data of the initial data recording group based on the weight attenuation gradient to obtain an adjusted data recording group; when an emergency event is detected, updating the weight attenuation gradient and the initial weight, and modifying the adjusted data recording group according to the updated weight attenuation gradient and the updated initial weight to obtain a transition data recording group; recording the transition data recording group according to the data recording group number to obtain a target data recording group, and completing the data recording of the event data recorder. The key event data is ensured to be preferentially stored.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of data recording, in particular to a data recording method and device of an event data recorder, equipment and a storage medium. BACKGROUND

[0002] When an automatic emergency braking (AEB) triggers braking, a certain period of data before and after the triggering needs to be recorded, including the state of the vehicle before triggering, the change of the perceived target, and the dynamic response after triggering. These data can help the vehicle manufacturer accurately understand the triggering conditions, judge the possibility of false triggering, and analyze the particularity of the target, so as to optimize the design of the AEB system, improve safety and reliability, and provide key basis for accident analysis, meeting the high requirements of users and regulatory agencies on vehicle safety performance. The event data recorder (EDR) data recording is usually recorded in a certain controller, and the controller has very limited storage space due to cost, design, etc., so only a fixed number of EDR data can be recorded.

[0003] In the traditional technical solution, a fixed time interval, such as every 0.5 seconds or every 0.1 seconds, is usually used to record a period of time before and after the triggering event, without distinguishing the importance of the event, and all data are stored with the same priority. However, due to the fixed recording interval and the lack of priority management, the storage space utilization is low, and key data may be missed, which cannot balance the recording range and data accuracy.

[0004] The above content is only used to assist in understanding the technical solutions of the present application and does not represent the acknowledgement of the above content as prior art. SUMMARY

[0005] The main purpose of the present application is to provide a data recording method, device, equipment and storage medium of an event data recorder, aiming to solve the technical problem of insufficient key event data recording accuracy under limited storage space.

[0006] To achieve the above purpose, the present application provides a data recording method of an event data recorder, which comprises:

[0007] obtaining a data recording group number, an initial weight and a weight attenuation gradient;

[0008] According to the initial weight, the event frame data is weighted to obtain initial event frame data, and the initial event frame data is stored in a data recording group to obtain an initial data recording group;

[0009] Based on the weight attenuation gradient, the target event frame data of the initial data recording group is deleted to obtain an adjusted data recording group;

[0010] updating the weight decay gradient and the initial weight when the emergency event is detected, and modifying the adjustment data record group according to the updated weight decay gradient and the updated initial weight to obtain a transition data record group;

[0011] recording the transition data record group according to the data record group number to obtain a target data record group, and completing data recording of the event data recorder.

[0012] In an embodiment, the emergency event includes a collision event.

[0013] The step of updating the weight decay gradient and the initial weight when the emergency event is detected, and modifying the adjustment data record group according to the updated weight decay gradient and the updated initial weight to obtain a transition data record group includes:

[0014] updating the initial weight to a collision initial weight and updating the weight decay gradient to a collision decay gradient when the collision event is detected;

[0015] obtaining a collision adjustment frame number and a current collision data frame;

[0016] adjusting the adjustment data record group according to the collision initial weight, the collision decay gradient, the current collision data frame, and the collision adjustment frame number to obtain a transition data record group.

[0017] In an embodiment, the emergency event further includes an emergency braking event.

[0018] The step of updating the weight decay gradient and modifying the adjustment data record group according to the updated weight decay gradient to obtain a transition data record group when the emergency braking event is detected includes:

[0019] updating the initial weight to a braking initial weight and updating the weight decay gradient to a braking decay gradient when the emergency braking event is detected;

[0020] obtaining a weight adjustment time interval, a data recording time interval, and a braking adjustment frame number;

[0021] obtaining a fixed weight event frame according to the weight adjustment time interval and the data recording time interval;

[0022] adjusting the adjustment data record group according to the braking initial weight, the braking decay gradient, the braking adjustment frame number, and the fixed weight event frame to obtain a transition data record group.

[0023] In an embodiment, after the step of updating the initial weight to a braking initial weight and updating the weight decay gradient to a braking decay gradient when detecting an emergency braking event, the method further comprises:

[0024] detecting whether a collision data frame exists in the adjustment data record group;

[0025] updating a collision decay gradient when detecting that the collision data frame exists in the adjustment data record group, and modifying a collision initial weight according to the updated collision decay gradient;

[0026] updating an event frame decay gradient when detecting that the collision data frame does not exist in the adjustment data record group, and modifying an event frame weight according to the updated event frame decay gradient.

[0027] In an embodiment, the step of obtaining the data record group number, the initial weight, and the weight decay gradient comprises:

[0028] obtaining a target storage space, a required storage space, a historical braking occurrence number, a data record time interval, an initial weight, and a data record time range;

[0029] calculating the data record group number according to the target storage space, the required storage space, and the historical braking occurrence number;

[0030] calculating the weight decay gradient according to the data record time interval and the data record time range.

[0031] In an embodiment, after the step of calculating the weight decay gradient according to the data record time interval and the data record time range, the method further comprises:

[0032] when the weight decay gradient is greater than the data record group number, calculating a frame loss parameter according to the weight decay gradient and the data record group number, and calculating a first time difference threshold according to the data record time interval and the frame loss parameter;

[0033] obtaining a second time difference threshold according to the data record time range;

[0034] obtaining first frame data and second frame data according to a current data record group, and obtaining a record time difference according to the first frame data and the current frame data;

[0035] deleting the first frame data or the second frame data according to the record time difference, the first time difference threshold, and the second time difference threshold.

[0036] In an embodiment, the step of deleting the first frame data or the second frame data according to the record time difference, the first time difference threshold, and the second time difference threshold comprises:

[0037] delete the first frame data when the recording time difference is greater than the second time difference threshold;

[0038] determine whether a time difference between the second frame data and the first frame data is less than a first time difference threshold when the recording time difference is less than or equal to the second time difference threshold;

[0039] delete the second frame data when the time difference between the second frame data and the first frame data is less than the first time difference threshold.

[0040] In addition, to achieve the above object, the present application further provides a data recording device of an event data recorder, which comprises a data acquisition module, configured to acquire a data recording group number, an initial weight and a weight attenuation gradient;

[0041] a data recording module, configured to weight event frame data according to the initial weight to obtain initial event frame data, store the initial event frame data into a data recording group to obtain an initial data recording group;

[0042] a data adjustment module, configured to delete target event frame data of the initial data recording group based on the weight attenuation gradient to obtain an adjusted data recording group;

[0043] a data updating module, configured to update the weight attenuation gradient and the initial weight when an emergency event is detected, and modify the adjusted data recording group according to the updated weight attenuation gradient and the updated initial weight to obtain a transition data recording group;

[0044] the data recording module is further configured to record the transition data recording group according to the data recording group number to obtain a target data recording group, and complete data recording of the event data recorder.

[0045] In addition, to achieve the above object, the present application further provides a data recording device of an event data recorder, which comprises a memory, a processor and a computer program stored in the memory and executable on the processor, and the computer program is configured to implement the steps of the data recording method of the event data recorder.

[0046] In addition, to achieve the above object, the present application further provides a storage medium, which is a computer readable storage medium, and the storage medium stores a computer program, and the computer program is executed by a processor to implement the steps of the data recording method of the event data recorder.

[0047] In addition, to achieve the above object, the application further provides a computer program product, which comprises a computer program, and the computer program realizes the steps of the data recording method of the event data recorder when executed by a processor.

[0048] The one or more technical solutions provided in the application have at least the following technical effects:

[0049] By introducing the dynamic initial weight, weight decay gradient and weight update mechanism triggered by emergency events, the process of event data recording is optimized. By obtaining the number of data recording groups, initial weight and weight decay gradient, the event frame data is weighted based on the initial weight, and is stored in the data recording group. By deleting unimportant event frame data based on the weight decay gradient, an adjusted data recording group is obtained. When an emergency event is detected, the weight decay gradient and the initial weight are updated, and the data recording group is modified according to the new weight decay gradient and the updated initial weight, thereby generating a transition data recording group. According to the number of data recording groups, the transition data is recorded to obtain a target data recording group, and the data recording is completed. Through the scheme, the problem of how to preferentially save key event data in the case of limited storage space is solved. Especially when an emergency event occurs, the key data related to the emergency event can be preferentially saved by dynamically adjusting the weight and the decay mechanism, thereby avoiding the storage of redundant data and ensuring the integrity and timeliness of the key data. Compared with the prior art, the dynamic adjustment of the weight and the decay gradient in the scheme makes the data recording more intelligent, maximizes the preservation of key event data in the limited storage space, and improves the storage efficiency and the accuracy of data analysis. BRIEF DESCRIPTION OF DRAWINGS

[0050] The accompanying drawings, which are incorporated in and constitute a part of the specification, illustrate embodiments consistent with the application and serve to explain the principles of the application together with the specification.

[0051] In order to more clearly illustrate the technical solutions in the embodiments of the application or the prior art, the accompanying drawings needed to be used in the embodiments or prior art description will be briefly introduced. Obviously, for those skilled in the art, other drawings can also be obtained based on these drawings without creative labor.

[0052] Figure 1 A flowchart is provided for the data recording method of the event data recorder according to Embodiment One of the application;

[0053] Figure 2 A flowchart is provided for the data recording method of the event data recorder according to Embodiment Two of the application;

[0054] Figure 3Brief flow diagram of data recording method of event data recorder provided for Embodiment Two of the present application;

[0055] Figure 4 Module structure diagram of data recording device of event data recorder provided for Embodiment Two of the present application;

[0056] Figure 5 Device structure diagram of hardware running environment involved in data recording method of event data recorder in Embodiment Two of the present application.

[0057] The object, function features and advantages of the present application will be further explained in combination with embodiments and with reference to the accompanying drawings. DETAILED DESCRIPTION

[0058] It should be understood that the specific embodiments described herein are only used to explain the technical solutions of the present application, and are not used to limit the present application.

[0059] In order to better understand the technical solutions of the present application, the following will be described in detail in combination with the accompanying drawings and specific embodiments.

[0060] The main solution of the embodiment of the present application is: obtaining data recording group number, initial weight and weight decay gradient; weighting the event frame data according to the initial weight to obtain initial event frame data, storing the initial event frame data into the data recording group to obtain the initial data recording group; deleting the target event frame data of the initial data recording group based on the weight decay gradient to obtain the adjusted data recording group; when detecting the emergency event, updating the weight decay gradient and the initial weight, and modifying the adjusted data recording group according to the updated weight decay gradient and the updated initial weight to obtain the transition data recording group; recording the transition data recording group according to the data recording group number to obtain the target data recording group, and completing the data recording of the event data recorder.

[0061] In the present embodiment, for the convenience of description, the following takes the data recording device of the event data recorder as the execution subject for elaboration.

[0062] In view of the insufficient precision of key event data record in the prior art under limited storage space, the application provides a solution. The process of event data record is optimized by introducing dynamic initial weight, weight decay gradient and weight updating mechanism triggered by emergency event. By obtaining the number of data record groups, initial weight and weight decay gradient, the event frame data is weighted based on the initial weight and stored in the data record groups. By deleting unimportant event frame data based on the weight decay gradient, the adjusted data record groups are obtained. When an emergency event is detected, the weight decay gradient and the initial weight are updated, and the data record groups are modified according to the new weight decay gradient and the updated initial weight, so as to generate a transition data record group. According to the number of data record groups, the transition data is recorded to obtain a target data record group, and the data record is completed. Through the scheme, the problem of how to preferentially save key event data under limited storage space is solved. Especially when an emergency event occurs, the key data related to the emergency event can be preferentially saved by dynamically adjusting the weight and the decay mechanism, the storage of redundant data is avoided, and the integrity and timeliness of the key data are guaranteed. Compared with the prior art, the dynamic adjustment of the weight and the decay gradient makes the data record more intelligent, maximizes the preservation of key event data in limited storage space, and improves the storage efficiency and the accuracy of data analysis.

[0063] It should be noted that the execution subject of the embodiment can be a computing service device with data processing, network communication and program running functions, such as a tablet computer, a personal computer, a mobile phone, etc., or an electronic device capable of realizing the above functions, a data recording device of an event data recorder, etc. The data recording device of the event data recorder is taken as an example to illustrate the embodiment and the following embodiments.

[0064] Based on this, the application provides an event data recorder data recording method, which is described with reference to Figure 1 , Figure 1 The flowchart of the first embodiment of the event data recorder data recording method of the application is shown in the figure.

[0065] In the embodiment, the event data recorder data recording method includes steps S10-S50:

[0066] Step S10, obtaining the number of data record groups, initial weight and weight decay gradient;

[0067] It should be noted that the number of data record groups refers to the maximum number of data groups that can be recorded in a given storage space. Each group of data contains event data in a specific time period. The number of record groups is determined according to the storage capacity, which determines the effective use of storage space and the number of recorded data.

[0068] In addition, the initial weight refers to the initial weight given to each event frame at the beginning of data recording. The initial weight can be determined according to factors such as event type, urgency, etc. In this embodiment, the initial weight can be 0.4.

[0069] In addition, the weight decay gradient refers to the rate at which the initial weight of the data gradually decreases over time or other factors. The weight decay gradient controls the change of the weight in the data storage process, ensuring that historical data that is no longer important over time is gradually replaced.

[0070] For example, suppose the system obtains 20 groups of data when recording event data, sets the initial weight of each frame to 0.5, and defines a decay gradient of 0.05 per second. The weight will gradually decrease according to the weight decay gradient, and when the weight is 0, the corresponding event frame data will be discarded.

[0071] Step S20, according to the initial weight, the event frame data is weighted, and the initial event frame data is obtained, and the initial event frame data is stored in the data recording group, and the initial data recording group is obtained;

[0072] It should be noted that the initial event frame data is the first frame data formed after the initial weight is assigned. The first frame data maintains the original weight and importance before further processing or decay.

[0073] In addition, the data recording group refers to a unit in which a plurality of related event frame data are stored together. Each group of data contains all event frame data within a certain time period and is stored in a separate data unit.

[0074] It can be understood that the event frame data is weighted according to the initial weight set in step S10. The weighted data is stored in a data recording group to obtain an initial data recording group.

[0075] Step S30, based on the weight decay gradient, deleting the target event frame data of the initial data recording group, obtaining an adjusted data recording group;

[0076] It should be noted that the target event frame data refers to the event frame data selected according to the current storage weight during the data recording process. The weight of the target event frame data has been reduced to 0, and it needs to be deleted in the storage process to release the storage space.

[0077] In addition, the adjusted data recording group refers to a new data recording group obtained by deleting the frame data that is no longer important based on the weight decay gradient and the storage strategy on the basis of the initial data recording group. The adjusted data group contains higher priority event data.

[0078] It can be understood that the unimportant target event frame data in the initial data record group is deleted according to the weight decay gradient to obtain the adjusted data record group. By reducing the weight through the decay gradient, it is determined which data still has a high value and which data can be discarded. Assuming that the weight of the initial event frame data is 0.5, but as time goes by, the decay gradient makes the weight of certain data decrease to 0, the low-weight data is deleted according to the change and the key data is retained.

[0079] In step S40, when the emergency event is detected, the weight decay gradient and the initial weight are updated, and the adjusted data record group is modified according to the updated weight decay gradient and the updated initial weight to obtain a transition data record group.

[0080] It should be noted that the emergency event refers to an event that needs to be responded immediately and has a high priority, such as a collision, AEB triggering, or other important safety events. These events usually need to be processed and recorded in priority for subsequent analysis.

[0081] In addition, the transition data record group refers to a temporary data record group that is adjusted according to the updated initial weight and weight decay gradient after the emergency event occurs. It contains data after the emergency event and has been adjusted according to the new priority.

[0082] It can be understood that when the emergency event is detected, the weight decay gradient and the initial weight are updated. The priority of the data record can be changed, and the emergency event data is given a higher weight. Based on the updated weight, the data record group is adjusted to contain more data related to the emergency event to obtain the transition data record group. Assuming that the vehicle detects an impending collision, data related to the collision is saved in priority, the initial weight and the decay gradient are updated, and the priority of the data in the record group is adjusted.

[0083] In a possible implementation, step S40 can include steps A41-A43.

[0084] In step A41, when the collision event is detected, the initial weight is updated to a collision initial weight, and the weight decay gradient is updated to a collision decay gradient.

[0085] It can be understood that the emergency event includes a collision event. During the driving of the vehicle, an object in front of the vehicle is identified, and a unique identifier, i.e., ID, is given to the object in front of the vehicle during the identification. In this embodiment, the emergency event includes but is not limited to the ID of the front target jumping, the time to collision (TTC) of the front target reaching a certain specific value, the vehicle colliding, the airbag exploding, etc.

[0086] It should be noted that the collision initial weight refers to the weight value assigned to the relevant event frame data when the collision event occurs. In this embodiment, the collision initial weight can be 0.8.

[0087] In addition, the collision attenuation gradient refers to the weight attenuation rate of the data after the collision event occurs. Since the priority of the collision data is high, the attenuation gradient can be set lower to ensure that the collision data can be retained for a longer period of time.

[0088] Step A42, obtaining the collision adjustment frame number and the current collision data frame;

[0089] It should be noted that the current collision data frame refers to the current frame data related to the collision event, which contains detailed information at the time of the event, such as vehicle state, perceived target, sensor data, etc.

[0090] In addition, the collision adjustment frame number refers to the frame number adjusted for optimizing data recording and storage when the collision event occurs. In this embodiment, the collision adjustment frame number can be the previous 2 frames and the next 2 frames of the current collision data frame.

[0091] Step A43, adjusting the adjustment data record group according to the collision initial weight, the collision attenuation gradient, the current collision data frame, and the collision adjustment frame number to obtain a transition data record group.

[0092] It can be understood that the data record group is adjusted according to the collision initial weight, the collision attenuation gradient, the current collision data frame, and the collision adjustment frame number to obtain a transition data record group. Specifically, the data of the collision adjustment frame number of the current collision data frame is fixed and adjusted, and these adjusted data are attenuated in weight according to the collision attenuation gradient.

[0093] For example, after the collision occurs, an initial weight of 0.8 is assigned to the collision frame, and the data of the previous 2 frames is adjusted. Among them, the data of the first previous frame is adjusted to a weight of 0.7, and the data of the second previous frame is adjusted to a weight of 0.6, and these collision data are attenuated in weight according to the collision attenuation gradient.

[0094] In a possible implementation, step S40 can include steps B41-B44:

[0095] Step B41, when detecting an emergency braking event, updating the initial weight to a braking initial weight and updating the weight attenuation gradient to a braking attenuation gradient;

[0096] It can be understood that the emergency event also includes an emergency braking event, which refers to the situation where AEB is triggered when the vehicle has a potential collision or needs to stop urgently. This event usually activates the brake system to force the vehicle to stop as soon as possible to avoid collision or reduce collision damage.

[0097] It should be noted that the braking initial weight is the initial weight assigned to the relevant data when the emergency braking event occurs. Since the braking event usually involves an emergency situation of the vehicle, the relevant data is given a higher initial weight so as to be quickly saved and processed preferentially. In this embodiment, the braking initial weight is the highest weight, i.e. 1.

[0098] In addition, the braking decay gradient refers to the decay rate of the weight of the emergency braking event related data over time. After the emergency braking event occurs, in order to ensure that the braking related data is saved preferentially in the emergency situation, the decay gradient is low, which means that these data will maintain a high priority for a long time.

[0099] In a possible implementation, after step B41, steps B411-B413 can be included:

[0100] Step B411, detecting whether there is a collision data frame in the adjusted data record group;

[0101] It can be understood that the adjusted data record group refers to the event data group adjusted by weight and frame number after the emergency event occurs. After step B41, it indicates that an emergency braking event has occurred.

[0102] It should be noted that the collision data frame refers to a single data record frame related to a collision event. These frames contain information about the state of the vehicle and sensor data when the collision occurs, and the collision data frame has a high priority and is usually used for subsequent accident analysis.

[0103] Step B412, when detecting that the collision data frame exists in the adjusted data record group, updating the collision decay gradient, and modifying the collision initial weight according to the updated collision decay gradient;

[0104] It can be understood that when an emergency braking event occurs and it is detected that the adjusted data record group contains a collision data frame, the collision decay gradient will be updated, and the collision initial weight will be updated according to the new decay gradient. By adjusting the decay gradient and the initial weight, it is ensured that the collision data can maintain a high priority for a long time after the event occurs, so as to better save the key data. Assuming that the initial weight of the collision data frame is 0.8 and the decay gradient is set to 0.1, the updated decay gradient is half of the original decay gradient, i.e. 0.05, so as to retain the high priority data related to the collision for a longer time.

[0105] Step B413, when detecting that there is no collision data frame in the adjusted data record group, updating the event frame decay gradient, and modifying the event frame weight according to the updated event frame decay gradient.

[0106] It should be noted that the event frame decay gradient refers to the rate of weight decay of data when a non-emergency event occurs. In addition, the event frame weight refers to the weight assigned to each event frame during data recording. Data with high weight is recorded first, and data with low weight is discarded first when storage space is limited.

[0107] It can be understood that when no collision data frame is detected, the decay gradient is adjusted according to the type and importance of the event, and after updating, the decay of the data is accelerated, so that unimportant event data is quickly replaced. For example, the data after AEB triggering has an initial weight of 0.4, and the decay gradient is set to 0.2. The weight will decay to 0 after 2 frames. After the maximum number of data records is reached, the minimum weight in the history frame is compared with the weight of the frame to be recorded, and the smaller weight is discarded and the larger weight is recorded.

[0108] Step B42, obtaining a weight adjustment time interval, a data recording time interval, and a brake adjustment frame number;

[0109] It should be noted that the weight adjustment time interval refers to the time interval used to adjust the weight of the data frame during data recording. In this embodiment, the data recording time interval can be 0.5s. With respect to the brake event frame, the data frame separated by the data recording time interval will be assigned a higher weight, which can better evaluate the AEB event.

[0110] In addition, the data recording time interval refers to the time interval at which the sensor records data. It determines how long the system records data every time. For example, the data recording time interval can be 0.1 seconds, which means that data is collected every 0.1 seconds. This interval usually depends on the minimum period of collecting sensor output to perceive the target.

[0111] In addition, the brake adjustment frame number refers to the number of frames adjusted and recorded during the emergency braking event in order to better capture the details of the event. Since the braking event can be relatively short, more frames are needed to record event data to ensure that all key information during the emergency braking process can be recorded completely. In this embodiment, the brake adjustment frame number can be 2 frames of data before and after the occurrence of braking.

[0112] Step B43, obtaining a fixed weight event frame according to the weight adjustment time interval and the data recording time interval;

[0113] It should be noted that the fixed weight event frame refers to the constant weight assigned to each event frame during data recording. The data of these frames remains unchanged during the weight adjustment process. The function of the fixed weight event frame is to ensure that important data is preferentially saved during an emergency event.

[0114] According to the weight adjustment time interval and the data recording time interval, a fixed weight event frame is generated. That is, according to the set weight adjustment time interval and the data recording time interval, the fixed weight event frame can be calculated, and the weight of each frame data of the fixed weight event frame remains unchanged. Assuming that data is recorded at an interval of 0.05 s during emergency braking, the weight adjustment time interval is 0.5 s, and the weight of the frame is set to 1 when the data of the frame is recorded to 0.5 s. In this way, the data in the emergency event will be recorded preferentially, and weight decay will not occur within the time interval.

[0115] Step B44, according to the brake initial weight, the brake decay gradient, the brake adjustment frame number and the fixed weight event frame, the transition data recording group is obtained by adjusting the adjustment data recording group.

[0116] It can be understood that according to the brake initial weight, the brake decay gradient, the brake adjustment frame number and the fixed weight event frame, the original data recording group is adjusted to generate a transition data recording group. Through this adjustment process, the system ensures that all important data is preferentially retained during an emergency braking event, and the weight and frame number of the data are adjusted according to the dynamic changes of the event. For example, assuming that the brake initial weight is set to 1, the brake decay gradient is set to 0.05, and 40 frames of data are recorded during emergency braking. Through this adjustment process, a transition data recording group is generated to ensure that all critical data is completely saved when the braking event occurs.

[0117] In addition, after the AEB is triggered, the data closest to the triggering time of the AEB is set to 1.

[0118] For example, after the AEB is triggered, the data closest to -1 s among -2 s, -1.5 s, -1 s and -0.5 s, such as -1.05 s, is set to 1. The data weight at the fixed time after the AEB is triggered is also set to 1. For example, 0.5 s, 0.1 s, etc. The data with the weight set to 1 is not decayed. Other data not set to 1 is decayed according to the brake decay gradient. At the same time, the data of the AEB triggering time and the front and rear brake adjustment frame number is decayed according to a certain value. For example, the data of the front and rear 2 frames, the weight of the front second frame is set to 0.8, the weight of the front first frame is set to 0.9, the weight of the rear first frame is set to 0.8, and the initial weight of the rear second frame is set to 0.6.

[0119] Step S50, according to the data recording group number, the transition data recording group is recorded to obtain a target data recording group, and the data recording of the event data recorder is completed.

[0120] It should be noted that the target data record group refers to the data record group that is finally selected and saved after all adjustments. It contains all important event data and meets the storage capacity requirements.

[0121] It can be understood that the updated transition data record group is saved as the target data record group according to the number of data record groups, and the entire data record process is completed. The system determines which data will be finally retained according to the storage capacity and the importance of the data. Assuming that the weight is updated and unnecessary data is deleted in the transition data record group, the most important record is finally saved as the target data record group, and the entire event data record is completed.

[0122] The embodiment provides a data recording method of an event data recorder. The data recording method of the event data recorder based on dynamic adjustment and data screening solves the technical problem of efficiently recording and managing important event data in a limited storage space, and achieves the beneficial effects of optimizing data storage, ensuring priority saving of key event data, and improving the overall performance of the data recording system.

[0123] Based on the first embodiment of the present application, in the second embodiment of the present application, the same or similar contents as the above-mentioned first embodiment can be referred to the above introduction, and will not be repeated hereinafter. On this basis, please refer to Figure 2 , the step S10 of the data recording method of the event data recorder further comprises steps S11-S13:

[0124] Step S11, obtaining a target storage space, a required storage space, a historical braking occurrence number, a data recording time interval, an initial weight, and a data recording time range;

[0125] It should be noted that the target storage space refers to the storage capacity of the maximum storage space, which is usually expressed in bytes or other storage units, and is used to store event data. The target storage space determines how many data records and data groups the system can save.

[0126] In addition, the required storage space refers to the occupied space of the required storage data of each group. The calculation of the required storage space is based on the amount of recorded data, the complexity of the data, and the required storage time.

[0127] In addition, the historical braking occurrence number refers to the number of times of emergency braking events that have occurred in the past operation process. This data helps to predict the frequency of future possible events of the system and adjust the demand for storage space.

[0128] In addition, the data recording time interval refers to the time interval at which the system collects event data. For example, if data is recorded every 0.1 second, the data recording time interval is 0.1 second. This parameter determines the accuracy and frequency of recording data.

[0129] Additionally, the data recording time range refers to the time period of data that needs to be recorded before and after an event. For example, data may need to be recorded from 1 second before an event to 2 seconds after it. This time range determines the length of the data recording and the amount of data that needs to be stored. The data recording time range includes before and after, and can specifically be [tbefore, tafter]. For example, tbefore is the time period before the AEB trigger moment, and tafter is the time period after the AEB trigger moment. For example, if the recording time period is specified to be from 2 seconds before to 3 seconds after the AEB trigger, then tbefore is -2 seconds and tafter is 3 seconds.

[0130] Step S12, calculating the number of data record groups according to the target storage space, the required storage space, and the number of historical braking occurrences;

[0131] It should be noted that the number of data record groups refers to the maximum number of data groups that the system can save within a given storage space. The number of data record groups is calculated based on storage capacity and event storage requirements.

[0132] The number of data record groups is calculated based on the target storage space, required storage space, and the number of historical braking events. The difference between the target and required storage space determines the amount of data the system can accommodate, while the number of historical braking events helps predict the frequency of future data recording. For example, if the frequency of historical braking events is high, the system may reserve more storage space for each event, affecting the calculation of the number of data record groups. The number of data record groups can be calculated as K = (M1 / M2) / n, where K is the number of data record groups, M1 is the target storage space, M2 is the required storage space, and n is the number of historical braking events. K is always an integer in the calculation.

[0133] Step S13: Calculate a weight attenuation gradient according to the data recording time interval and the data recording time range.

[0134] It should be noted that the weight decay gradient refers to the rate at which the weight of data changes over time. During the storage process, the weight of data gradually decays over time to ensure that no longer important or outdated data can be replaced by new data.

[0135] It can be understood that the weight decay gradient is calculated according to the data recording time interval and the data recording time range. First, t represents the data time period required to be recorded before AEB triggering, for example, it can be 2 seconds, indicating that the data within 2 seconds before the AEB event occurs needs to be recorded. The minimum time interval T is the time interval between each frame of data recording, for example, data is recorded every 0.05 seconds. The combination of the two parameters can determine the minimum number of data groups required to be recorded before AEB triggering, referred to as k, and the calculation formula is: k = t / T. Taking t = 2 seconds and T = 0.05 seconds as an example, k will be 40, indicating that 40 frames of data need to be recorded within the 2-second time period before AEB triggering. Next, the initial weight W basis value will be set to a suitable initial value (for example, 0.4), which represents the weight assigned when the first frame of data is recorded. Then, according to the value of k and the basis weight, the decay gradient is calculated. The calculation formula of the decay gradient is: decay gradient = W basis value / k. For example, if the basis weight W is 0.4 and k is 40, then the decay gradient is 0.4 / 40 = 0.01. This means that the weight decreases by 0.01 every time a frame of data is recorded. Therefore, during the data recording process, every time interval, in this embodiment, 0.05 seconds, the weight of the data frame decreases by 0.01. When the 41st group of data is generated, the weight of the first group of data will decrease to 0, at which time the data will be discarded directly, ensuring that in the case of limited storage space, the most recent and important data is saved first.

[0136] Through this process, the system can dynamically adjust the priority of data recording according to the time range of the event, the recording interval, and the limitation of the storage space, thereby achieving effective management of data and ensuring that critical event data can be saved first, avoiding the occupation of storage space by outdated or unimportant data.

[0137] In a feasible implementation, after the step of step S13, steps S14-S17 can be included:

[0138] Step S14, when the weight decay gradient is greater than the data recording group number, calculating a frame skipping parameter according to the weight decay gradient and the data recording group number, and calculating a first time difference threshold according to the data recording time interval and the frame skipping parameter;

[0139] It can be understood that when the weight decay gradient is less than or equal to the data recording group number, the data integrity before AEB triggering can be guaranteed. However, if the weight decay gradient is greater than the data recording group number, there is a problem of insufficient time before triggering, at which time it is necessary to discard according to frame skipping.

[0140] It should be noted that the frame loss parameter refers to a parameter used to calculate which data frames should be discarded. The parameter is calculated based on the weight decay gradient and the storage requirement of the data. The calculation of the frame loss parameter helps to prioritize the retention of the most important data frames in the case of limited storage space.

[0141] In addition, the first time difference threshold refers to the maximum time difference between data frames allowed when calculating frame loss. This threshold is used to determine whether the time difference between two data frames meets the frame loss condition.

[0142] It can be understood that the frame loss parameter can be calculated by the weight decay gradient and the number of data record groups, frame loss parameter n1=kfront / K. Where kfront is the weight decay gradient, and K is the number of data record groups.

[0143] The first time difference threshold can be calculated by the data record time interval and the frame loss parameter. The first time difference threshold is calculated by multiplying the data record time interval by the frame loss parameter.

[0144] Step S15, obtaining a second time difference threshold according to the data record time range;

[0145] It can be understood that the second time difference threshold refers to the time difference limit calculated according to the data record time range, which is used to determine whether the time interval between two data frames meets the storage condition. This threshold is usually determined according to the duration of the event and the recording interval of the data, and the purpose is to ensure that the data will not be discarded within the key time period of the event data. In this embodiment, the second time difference threshold is tfront of the data record time range, i.e. the front range.

[0146] Step S16, obtaining a first frame data and a second frame data according to the current data record group, and obtaining a record time difference according to the first frame data and the current frame data;

[0147] It should be noted that the first frame data refers to the earliest frame data in the current record group. It is usually recorded from the first moment after the event occurs, and has a high priority. The second frame data refers to another frame data in the current record group, which usually has a certain time difference with the first frame data.

[0148] It can be understood that the record time difference refers to the time difference between two frames of data, which is usually calculated by the data timestamp recorded by the system. The time difference is used to determine whether the two frames of data meet the storage condition, and then decide whether frame loss is needed.

[0149] Step S17, deleting the first frame data or the second frame data according to the record time difference, the first time difference threshold and the second time difference threshold.

[0150] It can be understood that deleting the first frame data or the second frame data means that during the data recording process, according to the set time difference threshold, it is determined to discard some data frames. The decision of deletion is made based on the time difference between the frames and the storage space requirement. According to the recording time difference and the previously calculated first time difference threshold and second time difference threshold, it is judged whether to delete the first frame data or the second frame data. If the time difference exceeds the threshold, the data is considered redundant, and the system will select to delete one of the frames of data to ensure that the storage space is effectively utilized.

[0151] In a feasible implementation, step S17 can include steps S171-S173:

[0152] Step S171, when the recording time difference is greater than the second time difference threshold, deleting the first frame data;

[0153] It can be understood that if the recording time difference is greater than the second time difference threshold, it will be decided to delete the first frame data. If the time interval between the two frames of data is large, it indicates that there may be insufficient correlation between them, and therefore the first frame data is considered to be no longer important and needs to be deleted. For example, if the time of the first frame is 0 seconds and the time of the second frame is 0.2 seconds, and the second time difference threshold is 0.1 seconds, then because the time difference is greater than the threshold, the first frame data will be deleted, and the subsequent frames will be filled in turn.

[0154] Step S172, when the recording time difference is less than or equal to the second time difference threshold, determining whether the time difference between the second frame data and the first frame data is less than the first time difference threshold;

[0155] It can be understood that it is judged whether the recording time difference is less than or equal to the second time difference threshold. It is ensured that when the system considers frame skipping, only data with a small time difference is frame skipped, because a large time difference between data frames usually means that there is a large interval between events. When the recording time difference is less than or equal to the second time difference threshold, it is further judged whether the time difference between the second frame data and the first frame data is less than the first time difference threshold. If the time difference between the second frame data and the first frame data is small, it indicates that they are closely related, and then the deletion judgment stage will be entered.

[0156] Step S173, when the time difference between the second frame data and the first frame data is less than the first time difference threshold, deleting the second frame data.

[0157] It can be understood that if the time difference between the second frame data and the first frame data is less than the first time difference threshold, it indicates that the two frame data are closely connected in time and have high redundancy, and therefore the second frame data can be discarded to complete the frame extraction. If the time difference between the second frame data and the first frame data is greater than or equal to the first time difference threshold, it is not discarded and is moved to the next frame to recalculate.

[0158] The embodiment provides a data recording method of an event data recorder. By introducing parameters such as a target storage space, a required storage space, a historical braking occurrence number, a data recording time interval and a time range, combining dynamic calculation of a weight decay gradient and optimization of a frame loss strategy, technical problems of efficiently recording and managing key event data in a limited storage space are solved, meanwhile, the integrity and priority of data recording are ensured, and beneficial effects of optimizing storage resource utilization, improving data recording system adaptability and flexibility are achieved.

[0159] Exemplarily, in order to help understand the implementation process of the data recording method of the event data recorder obtained after the embodiment one is combined with the above embodiment, please refer to Figure 3 , Figure 3 A brief flowchart of a data recording method of an event data recorder is provided, and specifically:

[0160] According to the total storage space of the EDR and the required space of each group of data, the system determines the maximum number of groups of EDR data storage. The system determines the minimum recording time interval according to the update frequency of the sensor, and further determines the time range before and after the AEB record. When the system records data, if no special event occurs, the system will allocate the basic recording weight, and these weights will decrease with the duration of the recording. For the occurrence of special events, adjustments will be made according to historical event records to ensure that the relevant weight allocation is reasonable at the time before and after the data recording. When a special event occurs (such as target ID jump, position degree change, etc.), the weight of the record will be adjusted according to the TTC (time to collision) moment. If the event occurs suddenly or is uncertain, the system will reduce the weight at the moment of occurrence to ensure that the record at the time is not disturbed by other events. When AEB is triggered, the system will preferentially ensure the closest recording data, ensuring that the data can be recorded in real time when an emergency event occurs. The maximum moment data in the time range is retained. After AEB is triggered, the system will record the event data. If a special event occurs, the system will preferentially allocate a higher weight when recording data to ensure that the special event data has a higher priority than the weight value of the basic event data. In this way, the system can ensure that important event data is saved in time and effectively for subsequent analysis and processing.

[0161] It should be noted that the above examples are only used for understanding the present application and do not constitute a limitation on the data recording method of the event data recorder, and more forms of simple transformation based on this technical concept are within the protection scope of the present application.

[0162] The present application also provides a data recording device of an event data recorder, which refers to Figure 4 The data recording device of the event data recorder comprises:

[0163] A data acquisition module 10 is configured to acquire a data recording group number, an initial weight, and a weight decay gradient.

[0164] A data recording module 20 is configured to weight event frame data according to the initial weight to obtain initial event frame data, store the initial event frame data into a data recording group, and obtain an initial data recording group.

[0165] A data adjustment module 30 is configured to delete target event frame data of the initial data recording group based on the weight decay gradient to obtain an adjusted data recording group.

[0166] A data updating module 40 is configured to update the weight decay gradient and the initial weight when an emergency event is detected, and modify the adjusted data recording group according to the updated weight decay gradient and the updated initial weight to obtain a transition data recording group.

[0167] The data recording module 20 is further configured to record the transition data recording group according to the data recording group number to obtain a target data recording group, and complete data recording of the event data recorder.

[0168] The data recording device of the event data recorder provided by the present application adopts the data recording method of the event data recorder in the above embodiments, and can solve the technical problem of insufficient key event data recording accuracy under limited storage space. Compared with the prior art, the data recording device of the event data recorder provided by the present application has the same beneficial effects as the data recording method of the event data recorder provided by the above embodiments, and other technical features in the data recording device of the event data recorder are the same as the features disclosed in the above embodiments, which will not be repeated here.

[0169] In an embodiment, the data updating module 40 is further configured to update the initial weight to a collision initial weight and update the weight decay gradient to a collision decay gradient when a collision event is detected, acquire a collision adjustment frame number and a current collision data frame, and adjust the adjusted data recording group according to the collision initial weight, the collision decay gradient, the current collision data frame, and the collision adjustment frame number to obtain a transition data recording group.

[0170] In an embodiment, the data updating module 40 is further configured to update the initial weight to a braking initial weight and update the weight decay gradient to a braking decay gradient when detecting an emergency braking event; obtain a weight adjustment time interval, a data recording time interval, and a braking adjustment frame number; obtain a fixed weight event frame according to the weight adjustment time interval and the data recording time interval; and obtain a transition data recording group by adjusting the adjustment data recording group according to the braking initial weight, the braking decay gradient, the braking adjustment frame number, and the fixed weight event frame.

[0171] In an embodiment, the data updating module 40 is further configured to detect whether a collision data frame exists in the adjustment data recording group; update a collision decay gradient and modify a collision initial weight according to the updated collision decay gradient when detecting that the collision data frame exists in the adjustment data recording group; and update an event frame decay gradient and modify an event frame weight according to the updated event frame decay gradient when detecting that the collision data frame does not exist in the adjustment data recording group.

[0172] In an embodiment, the data obtaining module 10 is further configured to obtain a target storage space, a demand storage space, a historical braking occurrence number, a data recording time interval, an initial weight, and a data recording time range; calculate a data recording group number according to the target storage space, the demand storage space, and the historical braking occurrence number; and calculate a weight decay gradient according to the data recording time interval and the data recording time range.

[0173] In an embodiment, the data obtaining module 10 is further configured to calculate a frame loss parameter according to the weight decay gradient and the data recording group number and calculate a first time difference threshold according to the data recording time interval and the frame loss parameter when the weight decay gradient is greater than the data recording group number; obtain a second time difference threshold according to the data recording time range; obtain first frame data and second frame data according to a current data recording group, and obtain a recording time difference according to the first frame data and the current frame data; and delete the first frame data or the second frame data according to the recording time difference, the first time difference threshold, and the second time difference threshold.

[0174] In an embodiment, the data obtaining module 10 is further configured to delete the first frame data when the recording time difference is greater than the second time difference threshold; determine whether a time difference between the second frame data and the first frame data is less than a first time difference threshold when the recording time difference is less than or equal to the second time difference threshold; and delete the second frame data when the time difference between the second frame data and the first frame data is less than the first time difference threshold.

[0175] The application provides a data recording device of an event data recorder, comprising: at least one processor; and a memory connected with the at least one processor in communication; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to perform the data recording method of the event data recorder in the first embodiment.

[0176] Reference will now be made to the drawings, in which Figure 5 which shows a structural schematic diagram of a data recording device of an event data recorder suitable for implementing the embodiments of the application. The data recording device of the event data recorder in the embodiments of the application can include, but is not limited to, mobile terminals such as mobile phones, notebook computers, digital broadcast receivers, PDAs (Personal Digital Assistant), PADs (Portable Application Description), PMPs (Portable MediaPlayer), vehicle-mounted terminals (such as vehicle-mounted navigation terminals), and the like, and fixed terminals such as digital TVs, desktop computers, and the like. Figure 5 The shown data recording device of the event data recorder is only an example, and should not bring any limitation to the functions and use range of the embodiments of the application.

[0177] As Figure 5As shown, the data recording device of the event data recorder can include a processing device 1001 (e.g., a central processing unit, a graphics processing unit, etc.) that can perform various appropriate actions and processes according to programs stored in a read only memory (ROM) 1002 or programs loaded from a storage device 1003 into a random access memory (RAM) 1004. Various programs and data required for the operation of the data recording device of the event data recorder are also stored in the RAM 1004. The processing device 1001, the ROM 1002, and the RAM 1004 are connected to each other through a bus 1005. An input / output (I / O) interface 1006 is also connected to the bus. Generally, the following systems can be connected to the I / O interface 1006: input devices 1007 including, for example, a touch screen, a touch pad, a keyboard, a mouse, an image sensor, a microphone, an accelerometer, a gyroscope, etc.; output devices 1008 including, for example, a liquid crystal display (LCD), a speaker, a vibrator, etc.; the storage device 1003 including, for example, a magnetic tape, a hard disk, etc.; and a communication device 1009. The communication device 1009 can allow the data recording device of the event data recorder to communicate wirelessly or wired with other devices to exchange data. Although the data recording device of the event data recorder with various systems is shown in the figure, it should be understood that all the shown systems are not required to be implemented or possessed. More or less systems can be alternatively implemented or possessed.

[0178] In particular, the processes described above with reference to the flowcharts can be implemented as computer software programs according to embodiments of the present disclosure. For example, embodiments of the present disclosure include a computer program product comprising a computer program carried on a computer readable medium, the computer program containing program code for performing the methods shown in the flowcharts. In such embodiments, the computer program can be downloaded and installed from a network through the communication device, or installed from the storage device 1003, or installed from the ROM 1002. When the computer program is executed by the processing device 1001, the above-mentioned functions defined in the methods of embodiments of the present disclosure are performed.

[0179] The data recording device of the event data recorder provided by the present disclosure adopts the data recording method of the event data recorder in the above-mentioned embodiments, and can solve the technical problem of insufficient key event data recording accuracy under limited storage space. Compared with the prior art, the data recording device of the event data recorder provided by the present disclosure has the same beneficial effects as the data recording method of the event data recorder provided by the above-mentioned embodiments, and other technical features in the data recording device of the event data recorder are the same as the features disclosed in the previous embodiment method, which will not be repeated here.

[0180] It should be understood that various aspects of the disclosure can be implemented in hardware, software, firmware, or a combination thereof. In the description of the embodiments above, specific features, structures, materials or characteristics can be combined in any suitable manner in one or more embodiments or examples.

[0181] The above description is merely illustrative of the application and is not intended to limit the scope of the application. Any variations and modifications that can be made by any person skilled in the art within the spirit and scope of the application are intended to be encompassed by the application. The scope of the application is defined by the appended claims.

[0182] The application provides a computer readable storage medium having stored thereon computer readable program instructions (i.e., a computer program) for performing the data recording method of the event data recorder in the above-described embodiments.

[0183] The computer readable storage medium provided by the application may, for example, be a U disk, but is not limited to an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, system, or device, or any combination thereof. More specific examples of the computer readable storage medium can include, but are not limited to, an electrical connection having one or more conductive wires, a portable computer diskette, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In the present embodiment, the computer readable storage medium can be any tangible medium that contains or stores a program that can be used by or in conjunction with an instruction execution system, system, or device. The program code contained on the computer readable storage medium can be transmitted in any suitable medium, including but not limited to electrical wire, optical cable, RF (Radio Frequency), etc., or any suitable combination thereof.

[0184] The above computer readable storage medium can be included in the data recording device of the event data recorder; or can exist separately and not be assembled into the data recording device of the event data recorder.

[0185] The computer readable storage medium described above carries one or more programs, when the one or more programs are executed by the data recording device of the event data recorder, cause the data recording device of the event data recorder to: acquire a number of data recording groups, an initial weight, and a weight decay gradient; weight the event frame data according to the initial weight to obtain initial event frame data, store the initial event frame data to the data recording groups to obtain initial data recording groups; delete target event frame data of the initial data recording groups based on the weight decay gradient to obtain adjusted data recording groups; when an emergency event is detected, update the weight decay gradient and the initial weight, and modify the adjusted data recording groups according to the updated weight decay gradient and the updated initial weight to obtain transition data recording groups; record the transition data recording groups according to the number of data recording groups to obtain target data recording groups, and complete data recording of the event data recorder.

[0186] Computer program code for carrying out operations of the present application can be written in any combination of one or more programming languages, including an object oriented programming language such as Java, Smalltalk, C++ or the like and conventional procedural programming languages, such as the "C" programming language or similar programming languages. The program code can execute entirely on the user's computer, partly on the user's computer, as a stand-alone software package, partly on the user's computer and partly on a remote computer or entirely on the remote computer or server. In the latter scenario, the remote computer can be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or the connection can be made to an external computer (for example, through the Internet using an Internet Service Provider).

[0187] The computer program instructions can also be loaded onto a computer or other programmable information processing apparatus to cause a series of operations to be performed on the computer or other programmable information processing apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable information processing apparatus implement the functions / acts specified in the flowchart and / or block diagram block or blocks. The flowchart and block diagram in the drawings illustrate the architecture, functionality, and operation of possible implementations of systems, methods and computer program products according to various embodiments of the present application. In this regard, each block in the flowchart or block diagrams can represent a module, segment, or portion of code, which comprises one or more executable instructions for implementing the specified logic functions. It should also be noted that in some alternative implementations, the functions noted in the blocks can occur out of the order noted in the figures. For example, two blocks shown in succession may, in fact, be executed substantially concurrently or the blocks may be executed in the reverse order, depending upon the functionality involved. It will also be noted that each block of the block diagrams and / or flowchart illustrations, and combinations thereof, can be implemented by special purpose hardware-based systems that perform the specified functions or acts, or combinations of special purpose hardware and computer instructions.

[0188] The modules described in the embodiments of the present application can be implemented in the form of software or in the form of hardware. In some cases, the name of the module does not constitute a limitation on the module itself.

[0189] The readable storage medium provided by the present application is a computer readable storage medium, which stores computer readable program instructions (i.e., a computer program) for executing the data recording method of the event data recorder, and can solve the technical problem of insufficient key event data recording accuracy under limited storage space. Compared with the prior art, the computer readable storage medium provided by the present application has the same beneficial effects as the data recording method of the event data recorder provided by the above-mentioned embodiments, and will not be repeated here.

[0190] The present application also provides a computer program product comprising a computer program, which, when executed by a processor, implements the steps of the data recording method of the event data recorder as described above.

[0191] The computer program product provided by the present application can solve the technical problem of insufficient key event data recording accuracy under limited storage space. Compared with the prior art, the computer program product provided by the present application has the same beneficial effects as the data recording method of the event data recorder provided by the above-mentioned embodiments, and will not be repeated here.

[0192] The above only describes some embodiments of the present application, and does not limit the patent scope of the present application. Any equivalent structural transformation, direct / indirect application in other related technical fields based on the technical concept of the present application, and the content of the specification and drawings are included in the patent protection scope of the present application.

Claims

1. A data recording method of an event data recorder, characterized by, The method comprises: acquiring a data record group number, an initial weight, and a weight decay gradient; weighting event frame data according to the initial weight to obtain initial event frame data, storing the initial event frame data into a data record group to obtain an initial data record group; based on the weight decay gradient, deleting target event frame data of the initial data record group to obtain an adjusted data record group; when an emergency event is detected, updating the weight decay gradient and the initial weight, and modifying the adjusted data record group according to the updated weight decay gradient and the updated initial weight to obtain a transition data record group; recording the transition data record group according to the data record group number to obtain a target data record group, and completing data recording of an event data recorder.

2. The method of claim 1, wherein, The emergency event comprises a collision event: The step of updating the weight decay gradient and the initial weight when the emergency event is detected, and modifying the adjusted data record group according to the updated weight decay gradient and the updated initial weight to obtain a transition data record group comprises: when the collision event is detected, updating the initial weight to a collision initial weight and updating the weight decay gradient to a collision decay gradient; acquiring a collision adjustment frame number and a current collision data frame; adjusting the adjusted data record group according to the collision initial weight, the collision decay gradient, the current collision data frame, and the collision adjustment frame number to obtain a transition data record group.

3. The method of claim 1, wherein, The emergency event further comprises an emergency braking event: The step of updating the weight decay gradient when the emergency braking event is detected, and modifying the adjusted data record group according to the updated weight decay gradient to obtain a transition data record group comprises: when the emergency braking event is detected, updating the initial weight to a braking initial weight and updating the weight decay gradient to a braking decay gradient; acquiring a weight adjustment time interval, a data recording time interval, and a braking adjustment frame number; obtaining a fixed weight event frame according to the weight adjustment time interval and the data recording time interval; adjusting the adjusted data record group according to the braking initial weight, the braking decay gradient, the braking adjustment frame number, and the fixed weight event frame to obtain a transition data record group.

4. The method of claim 3, wherein, After the step of updating the initial weight to a braking initial weight and updating the weight decay gradient to a braking decay gradient when the emergency braking event is detected, the method further comprises: detecting whether there is a collision data frame in the adjusted data record group; when it is detected that there is the collision data frame in the adjusted data record group, updating a collision decay gradient and modifying a collision initial weight according to the updated collision decay gradient; when it is detected that there is no collision data frame in the adjusted data record group, updating an event frame decay gradient and modifying an event frame weight according to the updated event frame decay gradient.

5. The method of claim 1, wherein, The step of acquiring the data record group number, the initial weight, and the weight decay gradient comprises: acquiring a target storage space, a required storage space, a historical braking occurrence number, a data recording time interval, an initial weight, and a data recording time range; According to the target storage space, the required storage space, and the historical braking occurrence number, a data record group number is calculated; According to the data record time interval and the data record time range, a weight decay gradient is calculated.

6. The method of claim 5, wherein, After the step of calculating the weight decay gradient according to the data record time interval and the data record time range, the method further comprises: When the weight decay gradient is greater than the data record group number, a frame loss parameter is calculated according to the weight decay gradient and the data record group number, and a first time difference threshold is calculated according to the data record time interval and the frame loss parameter; A second time difference threshold is obtained according to the data record time range; First frame data and second frame data are obtained according to a current data record group, and a record time difference is obtained according to the first frame data and the current frame data; According to the record time difference, the first time difference threshold, and the second time difference threshold, the first frame data or the second frame data is deleted.

7. The method of claim 6, wherein, The step of deleting the first frame data or the second frame data according to the record time difference, the first time difference threshold, and the second time difference threshold comprises: When the record time difference is greater than the second time difference threshold, the first frame data is deleted; When the record time difference is less than or equal to the second time difference threshold, it is determined whether the time difference between the second frame data and the first frame data is less than the first time difference threshold; When the time difference between the second frame data and the first frame data is less than the first time difference threshold, the second frame data is deleted.

8. A data recording apparatus of an event data recorder, characterized by comprising: The device comprises: A data acquisition module for acquiring a data record group number, an initial weight, and a weight decay gradient; A data record module for weighting event frame data according to the initial weight to obtain initial event frame data, and storing the initial event frame data into a data record group to obtain an initial data record group; A data adjustment module for deleting target event frame data of the initial data record group based on the weight decay gradient to obtain an adjusted data record group; A data update module for updating the weight decay gradient and the initial weight when an emergency event is detected, and modifying the adjusted data record group according to the updated weight decay gradient and the updated initial weight to obtain a transition data record group; The data record module is further configured to record the transition data record group according to the data record group number to obtain a target data record group, and complete data recording of the event data recorder.

9. A data recording apparatus of an event data recorder, characterized by comprising: The device comprises a memory, a processor, and a computer program stored on the memory and executable on the processor, and the computer program is configured to implement the steps of the data recording method of the event data recorder according to any one of claims 1 to 7.

10. A storage medium, characterized by The storage medium is a computer readable storage medium, and the storage medium stores a computer program, and the computer program is executed by a processor to implement the steps of the data recording method of the event data recorder according to any one of claims 1 to 7.

Images