A driving data processing method, device and equipment, and a storage medium

Abstract

The application relates to a driving data processing method, device and equipment and a storage medium, wherein the driving data processing method comprises the following steps: acquiring at least one first data packet determined from driving data of a target vehicle and identification information of each first data packet; determining at least one second data packet with identification information satisfying a first preset condition from the at least one first data packet; and analyzing the at least one second data packet to obtain event trigger information of the target vehicle in a shadow mode. The application determines the second data packet with the identification information satisfying the first preset condition from the first data packet, analyzes the second data packet, obtains the event trigger information of the target vehicle in the shadow mode, can screen the driving data, further realizes customized analysis of the data, and improves the processing and analysis efficiency of a large amount of data.

Description

Technical Field

[0001] This application relates to the field of autonomous driving technology, specifically to a method, apparatus, device, and storage medium for processing driving data. Background Technology

[0002] Autonomous driving technology typically includes high-precision maps, environmental perception, path planning, and path tracking control. Training autonomous driving models requires collecting relevant driving data. However, the customization capabilities of related driving data analysis software are relatively low, failing to meet the needs of customized data analysis. Summary of the Invention

[0003] The purpose of this application is to provide a method, apparatus, device, and storage medium for processing driving data, in order to solve the problem that the customization level of relevant driving data analysis software in the prior art of autonomous driving is low and cannot meet the needs of customized data analysis.

[0004] To achieve the above objectives, the technical solution adopted in this application is as follows:

[0005] On one hand, this embodiment provides a method for processing driving data, the method including:

[0006] Acquire at least one first data packet determined from the driving data of the target vehicle, and identification information for each first data packet;

[0007] From at least one of the first data packets, determine at least one second data packet whose identification information satisfies a first preset condition;

[0008] At least one of the second data packets is parsed to obtain the event triggering information of the target vehicle in shadow mode.

[0009] Based on the above technical means, by determining the second data packet whose identification information meets the first preset condition from the first data packet, and parsing the second data packet, the event triggering information of the target vehicle in shadow mode can be obtained. Driving data can be filtered according to the first preset condition, thereby realizing customized data analysis and improving the processing and analysis efficiency of large batches of data.

[0010] Furthermore, the driving data of the target vehicle includes at least one data file, and the identification information includes topic information; obtaining at least one first data packet determined from the driving data of the target vehicle, and the identification information of each first data packet, includes:

[0011] Retrieve the third data packet corresponding to each of the data files from the message queue; wherein each of the third data packets is obtained by encoding the data file.

[0012] Each of the third data packets is decoded to obtain at least one first data packet and the subject information of each first data packet.

[0013] Based on the above technical means, by determining the topic information corresponding to the first data packet, and then based on the correspondence between the first data packet and the topic information, the required data can be accurately obtained from a large amount of data.

[0014] Furthermore, each of the second data packets has identification information and a timestamp, and the event triggering information includes the triggering time of the first event triggered by the target vehicle in shadow mode, as well as the target information associated with the first event;

[0015] The step of parsing at least one of the second data packets to obtain the event triggering information of the target vehicle in shadow mode includes:

[0016] Each of the second data packets is parsed to obtain the first information set corresponding to each of the second data packets;

[0017] Based on the timestamps of each first information set and the second data packets corresponding to each first information set, the triggering time of the first event triggered by the target vehicle in shadow mode is determined.

[0018] Based on the triggering time, target information associated with the first event is obtained from at least one of the first information sets; the target information includes at least one of the following: vehicle information, algorithm state information of the shadow mode, and perception information that triggered the first event.

[0019] Based on the above technical means, vehicle information associated with the first event, algorithm state information of the shadow mode, and / or perception information that triggered the first event can be quickly obtained from at least one first information set at the trigger time of the first event, thereby facilitating subsequent analysis and / or processing of the first event.

[0020] Furthermore, each of the first information sets includes at least trigger flag information, and the trigger flag information in each of the first information sets is used to characterize whether the first event is triggered at the time indicated by the timestamp of the second data packet corresponding to the first information set;

[0021] Determining the trigger time of the first event triggered by the target vehicle in shadow mode based on the timestamps of each first information set and the second data packet corresponding to each first information set includes:

[0022] From at least one of the first information sets, a second information set is determined; the triggering flag information in the second information set is a first flag value, the first flag value indicating that the first event was triggered at the time indicated by the timestamp of the second data packet corresponding to the second information set;

[0023] Based on the timestamp of the second data packet corresponding to the second information set, the triggering time of the first event triggered by the target vehicle in shadow mode is determined.

[0024] Based on the aforementioned technical means, the corresponding timestamp is determined based on the trigger flag information, thereby determining the trigger time of the first event triggered by the target vehicle in shadow mode, which can improve the accuracy and real-time performance of obtaining the trigger time of the first event.

[0025] Furthermore, the step of obtaining target information associated with the first event from at least one of the first information sets based on the triggering time includes:

[0026] When the target information includes the algorithm state information of the shadow mode, a third information set whose corresponding timestamp matches the trigger time is determined from at least one of the first information sets, and the algorithm state information of the shadow mode associated with the first event is obtained from the third information set.

[0027] If the target information includes vehicle information, a fourth information set matching the timestamp of the triggering time is determined from at least one of the first information sets, and vehicle information associated with the first event is obtained from the fourth information set.

[0028] If the target information includes the perception information that triggers the first event, a fourth information set is determined from at least one of the first information sets that matches the time preceding the triggering time, and the perception information that triggers the first event is obtained from the fourth information set.

[0029] Based on the aforementioned technical means, by acquiring algorithm state information, vehicle information, and perception information that match the triggering time, a comprehensive analysis of driving data related to the triggering time can be performed, thereby improving the processing capability of large amounts of driving data.

[0030] Furthermore, the first event includes at least one of the following: automatic emergency braking event, automatic emergency steering event, lane departure warning event; and / or, the vehicle information includes at least one of the following: chassis information, vehicle bus information.

[0031] Based on the above technical means, the first event can be one of multiple events, which can expand the application scenarios of this application for driving data processing. In addition, the vehicle information can be one of chassis information and vehicle bus information, which can improve the data correlation of vehicle data associated with the first event, thereby improving the efficiency of subsequent processing of the first event.

[0032] Furthermore, the method also includes: generating a data report based on the triggering time of the first event triggered by the target vehicle in shadow mode and the target information associated with the first event.

[0033] Based on the aforementioned technical means, by generating data reports, the processing results of driving data can be presented intuitively, thereby improving the efficiency of handling first events.

[0034] On the other hand, embodiments of this application provide a driving data processing apparatus, including:

[0035] The acquisition module is used to acquire at least one first data packet determined from the driving data of the target vehicle, and identification information of each first data packet;

[0036] The first determining module is configured to determine, from at least one first data packet, at least one second data packet whose identification information satisfies a first preset condition;

[0037] The second determining module is used to parse at least one of the second data packets to obtain the event triggering information of the target vehicle in shadow mode.

[0038] In another aspect, embodiments of this application provide a computer device, including a memory and a processor, wherein the memory stores a computer program that can run on the processor, and the processor executes the program to implement some or all of the steps in the above-described method.

[0039] In another aspect, embodiments of this application provide a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements some or all of the steps in the above-described method.

[0040] In another aspect, embodiments of this application provide a computer program including computer-readable code, wherein when the computer-readable code is run in a computer device, a processor in the computer device performs some or all of the steps for implementing the above-described method.

[0041] In another aspect, embodiments of this application provide a computer program product, the computer program product including a non-transitory computer-readable storage medium storing a computer program, wherein when the computer program is read and executed by a computer, it implements some or all of the steps in the above method.

[0042] The beneficial effects of this application are:

[0043] (1) This application determines the second data packet whose identification information meets the first preset condition from the first data packet, parses the second data packet, obtains the event triggering information of the target vehicle in the shadow mode, and can filter the driving data according to the first preset condition, thereby realizing customized data analysis and improving the processing and analysis efficiency of large batches of data.

[0044] (2) This application can quickly obtain vehicle information associated with the first event, algorithm state information of the shadow mode, and / or perception information that triggers the first event from at least one first information set at the trigger time of the first event, thereby facilitating subsequent analysis and / or processing of the first event. Attached Figure Description

[0045] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with this application and, together with the specification, serve to explain the technical solutions of this application.

[0046] Figure 1 A schematic diagram illustrating the implementation flow of a driving data processing method provided in an embodiment of this application;

[0047] Figure 2 A schematic diagram illustrating the implementation flow of a driving data processing method provided in an embodiment of this application;

[0048] Figure 3 A schematic diagram illustrating the implementation flow of a driving data processing method provided in an embodiment of this application;

[0049] Figure 4 This is a schematic diagram of the composition structure of a driving data processing device provided in an embodiment of this application;

[0050] Figure 5 This is a schematic diagram of the hardware entity of a computer device provided in an embodiment of this application. Detailed Implementation

[0051] The embodiments of this application will be described below with reference to the accompanying drawings and preferred embodiments. Those skilled in the art can easily understand other advantages and effects of this application from the content disclosed in this specification. This application can also be implemented or applied through other different specific embodiments, and various details in this specification can also be modified or changed based on different viewpoints and applications without departing from the spirit of this application. It should be understood that the preferred embodiments are only for illustrating this application and are not intended to limit the scope of protection of this application.

[0052] It should be noted that the illustrations provided in the following embodiments are only schematic representations of the basic concept of this application. Therefore, the drawings only show the components related to this application and are not drawn according to the actual number, shape and size of the components in the actual implementation. In the actual implementation, the form, quantity and proportion of each component can be arbitrarily changed, and the layout of the components may also be more complex.

[0053] This embodiment proposes a method for processing driving data, such as... Figure 1 As shown, the method includes the following steps S101 to S103:

[0054] Step S101: Obtain at least one first data packet determined from the driving data of the target vehicle, and identification information of each first data packet.

[0055] Here, the driving data of the target vehicle may include, but is not limited to, at least one of the following: sensor data, vehicle status data, target recognition data, and vehicle decision and control data.

[0056] Step S102: From at least one first data packet, determine at least one second data packet whose identification information satisfies a first preset condition.

[0057] Here, the identification information of the first data packet is used to classify the first data packet. The identification information is the category information corresponding to the first data packet, and the first preset condition is the preset category condition.

[0058] In some implementations, at least one second data packet whose identification information satisfies a preset category condition can be selected from at least one first data packet.

[0059] Step S103: parse at least one of the second data packets to obtain the event triggering information of the target vehicle in shadow mode.

[0060] In this embodiment of the application, by matching and filtering at least one second data packet whose identification information meets the preset category conditions from at least one first data packet, and parsing the second data packet, the event triggering information of the target vehicle in shadow mode can be obtained. Driving data can be filtered according to the first preset conditions, thereby realizing customized data analysis and improving the processing and analysis efficiency of large batches of data.

[0061] In some embodiments, each of the second data packets has identification information and a timestamp, and the event triggering information includes the triggering time of the first event triggered by the target vehicle in shadow mode, and target information associated with the first event; the step S103 above, which involves parsing at least one of the second data packets to obtain the event triggering information of the target vehicle in shadow mode, may include steps S111 to S113:

[0062] Step S111: Parse each of the second data packets to obtain the first information set corresponding to each of the second data packets.

[0063] In some implementations, each second data packet can be parsed separately, the parsed data can be stored in the form of a multi-level dictionary, and the data stored in the form of a multi-level dictionary can be structurally decomposed to obtain data stored in the form of a single-level dictionary.

[0064] Step S112: Based on the timestamps of each first information set and the second data packets corresponding to each first information set, determine the triggering time of the first event triggered by the target vehicle in shadow mode.

[0065] In some implementations, the target vehicle sets a preset condition to trigger the first event in shadow mode. Based on vehicle-related data stored in the form of a single-layer dictionary, the preset condition is triggered in the real-world environment. After the preset condition is triggered, the timestamp of the second data packet corresponding to the vehicle-related data stored in the form of a single-layer dictionary that triggers the preset condition for the first event in shadow mode is determined.

[0066] Step S113: Based on the triggering time, obtain target information associated with the first event from at least one of the first information sets; the target information includes at least one of the following: vehicle information, algorithm state information of the shadow mode, and perception information that triggered the first event.

[0067] There are various ways that those skilled in the art can obtain the perception information that triggers the first event, and this application embodiment is not limited to any particular method. For example, perception information related to the vehicle during autonomous driving can be obtained in real time through laser sensors, radar sensors, acoustic sensors, and cameras.

[0068] In some implementations, the first information that is concentrated within a preset time threshold of the timestamp corresponding to the trigger time can be identified as the target information associated with the first event.

[0069] In this embodiment of the application, the first information that is concentrated within a preset time threshold of the timestamp corresponding to the triggering time of the first event can be determined as the target information associated with the first event by the triggering time of the first event. Vehicle information associated with the first event, algorithm state information of shadow mode, and / or perception information that triggers the first event can be quickly obtained from at least one set of first information, thereby facilitating subsequent analysis and / or processing of the first event.

[0070] In some embodiments, each of the first information sets includes at least trigger flag information, and the trigger flag information in each of the first information sets is used to characterize whether the first event is triggered at the time indicated by the timestamp of the second data packet corresponding to the first information set; the step S112 above, which determines the trigger time of the target vehicle triggering the first event in shadow mode based on each of the first information sets and the timestamp of the second data packet corresponding to each of the first information sets, may include steps S121 to S123:

[0071] Step S121: Determine a second information set from at least one of the first information sets; the trigger flag information in the second information set is a first flag value, the first flag value indicating that the first event was triggered at the time indicated by the timestamp of the second data packet corresponding to the second information set.

[0072] Step S122: Based on the timestamp of the second data packet corresponding to the second information set, determine the triggering time when the target vehicle triggers the first event in shadow mode.

[0073] In this embodiment, the corresponding timestamp is determined based on the trigger flag information, thereby determining the trigger time of the first event triggered by the target vehicle in shadow mode, which can improve the accuracy and real-time performance of obtaining the trigger time of the first event.

[0074] In some embodiments, obtaining target information associated with the first event from at least one of the first information sets based on the triggering time in step S113 above may include steps S131 to S133:

[0075] Step S131: If the target information includes the algorithm state information of the shadow mode, determine a third information set whose corresponding timestamp matches the trigger time from at least one of the first information sets, and obtain the algorithm state information of the shadow mode associated with the first event from the third information set.

[0076] Here, shadow mode can be understood as the ability to identify scenes or scenes of interest containing irregularly shaped objects through built-in algorithms, and to record and store the identified special scenes or scenes of interest.

[0077] In some implementations, a third information set can also be determined from at least one first information set, with the corresponding timestamp falling within a time threshold before and after the triggering time.

[0078] Step S132: If the target information includes vehicle information, determine a fourth information set from at least one of the first information sets that matches the time preceding the triggering time, and obtain vehicle information associated with the first event from the fourth information set.

[0079] Step S133: If the target information includes the perception information that triggers the first event, determine a fourth information set from at least one of the first information sets whose corresponding timestamp matches the time before the triggering time, and obtain the perception information that triggers the first event from the fourth information set.

[0080] In this embodiment of the application, by acquiring algorithm state information, vehicle information, and perception information related to the triggering time, a comprehensive analysis of driving data related to the triggering time can be performed, thereby improving the processing capability of large amounts of driving data.

[0081] This embodiment provides an image classification method, such as Figure 2 As shown, the method includes the following steps S201 to S204:

[0082] Step S201: Obtain the third data packet corresponding to each data file in the driving data of the target vehicle from the message queue; wherein each third data packet is obtained by encoding the data file.

[0083] Here, message queues can improve the speed of retrieving the third data packet corresponding to each data file. The types of message queues include, but are not limited to, any one of the following: Kafka (an open source message queue component), KubeMQ (an open source message queue component), Pulsar (an open source message queue component), and RocketMQ (an open source message queue component).

[0084] Step S202: Decode each of the third data packets to obtain at least one first data packet and identification information for each first data packet; wherein the identification information includes topic information.

[0085] Here, the topic information must include at least the topic name. The topic name is used to represent the name of the topic information.

[0086] In some implementations, each third data packet can be decoded separately to obtain the corresponding binary data stream and timestamp. Here, each binary data stream corresponds to a timestamp and a topic name.

[0087] Step S203: From at least one first data packet, determine at least one second data packet whose identification information satisfies a first preset condition.

[0088] Step S204: parse at least one of the second data packets to obtain the event triggering information of the target vehicle in shadow mode.

[0089] Here, steps S203 and S204 correspond to steps S102 and S103 in the foregoing embodiments, respectively. When implementing these steps, the specific implementation methods of steps S102 and S103 can be referred to.

[0090] In some embodiments, the first event includes at least one of the following: automatic emergency braking event, automatic emergency steering event, lane departure warning event; and / or, the vehicle information includes at least one of the following: chassis information, vehicle bus information.

[0091] In this embodiment, the first event can be one of a variety of events, thereby expanding the application scenarios of this application for driving data processing. In addition, the vehicle information can be one of chassis information or vehicle bus information, which can improve the data correlation of vehicle data associated with the first event, thereby improving the efficiency of subsequent processing of the first event.

[0092] In some embodiments, the method for processing driving data further includes step S211:

[0093] Step S211: Generate a data report based on the triggering time of the first event triggered by the target vehicle in shadow mode and the target information associated with the first event.

[0094] During implementation, data reports are used to visualize the trigger time of the first event and the target information associated with the first event, so that developers or other personnel can browse and analyze the data.

[0095] In this embodiment of the application, by generating data reports, the processing results of driving data can be presented intuitively, thereby improving the processing efficiency of the first event.

[0096] The following describes the application of the driving data processing method provided in this embodiment in a real-world scenario, using an autonomous driving scenario as an example.

[0097] In related technologies, the amount of real-vehicle test data for autonomous driving algorithm modules is increasing, but commercial data analysis software has a low degree of customization and cannot meet the needs of customized data analysis; at the same time, large-scale data analysis cannot be achieved using commercial data analysis software.

[0098] This embodiment provides a method for processing driving data, such as Figure 3 As shown, the method includes the following steps S301 to S305:

[0099] Step S301: Obtain at least one first data packet determined from the driving data of the target vehicle, and identification information of each first data packet; wherein the driving data of the target vehicle includes at least one data file, and the identification information includes topic information.

[0100] In some implementations, before acquiring the driving data of the target vehicle, the directory location of the required driving data, the pb2.py file corresponding to the Proto file (message protocol file), and the topic and version information of the required driving data can be configured in the configuration file.

[0101] In some implementations, the Python programming language can be used to decompose and merge the structure and content of data files, and various Python libraries and custom libraries can be used, including but not limited to: at least one of the following libraries: os, Pandas, Struct, sys, JSON, DateTime, re, and bisect. Additionally, custom libraries require the library's location to be added to the environment variable sys.path.append before importing, for example: (os.path.dirname(os.path.dirname(os.path.realpath(__file__)))).

[0102] In some implementations, the `os.walk()` function can be used to traverse all data file addresses, and the data in the file corresponding to each data file address can be treated as data to be analyzed and queued into a message queue. The filenames of the temporary data can be obtained using the `split()` and `os.path.basename()` functions, and the first data packet can be parsed using the `struct.unpack()` function. The first data packet includes the required data header and data body. The data body includes the first data packet in binary data stream form (i.e., message information), and the data header includes topic information and timestamp information. All data files include files corresponding to vehicle data, perception information, and algorithm status information, and each data file address corresponds to one piece of data to be processed.

[0103] Step S302: From at least one first data packet, determine at least one second data packet whose identification information satisfies the first preset condition; wherein each second data packet has identification information and a timestamp, and the event triggering information includes the triggering time of the automatic emergency braking event triggered by the target vehicle in shadow mode, and the target information associated with the automatic emergency braking event.

[0104] In some embodiments, the first data packet in the form of binary data can be parsed through topic.ParseFromString, the topic information corresponding to the first data packet is matched with the preset topic information required, and the first data packet whose topic information meets the conditions of the preset topic information is determined as the second data packet, and a timestamp is appended to the second data packet through the append() function method and saved as the second data packet in the DataFrame structure; wherein, DataFrame is a tabular data structure.

[0105] Step S303: Parse each second data packet to obtain a first information set corresponding to each second data packet.

[0106] In some embodiments, the second data packet includes perception fusion data, self-vehicle chassis power data, and self-vehicle chassis status data. The perception fusion data, self-vehicle chassis power data, and self-vehicle chassis status data involve a multi-level structure. All signal names and signal values in the second data packet can be extracted to the outermost layer through a loop traversal method, temporarily stored in a dictionary structure, and appended into a new signal DataFrame structure of the first information set through the append() function method.

[0107] Step S304: Based on each first information set and the timestamp of the second data packet corresponding to each first information set, determine the trigger moment when the target vehicle triggers an automatic emergency braking event in the shadow mode.

[0108] Step S305: Based on the trigger moment, obtain target information associated with the automatic emergency braking event from at least one first information set; the target information includes at least one of the following: vehicle information, algorithm status information of the shadow mode, and perception information for triggering the automatic emergency braking event.

[0109] In some embodiments, the timestamp information, perception information, trigger flag bit information, and other algorithm-related information at the time of algorithm triggering are found through the methods of input_df.loc[(input_df[trigger signal]==1)] and dataframe[signal name].values. By presetting a dictionary of binary flag bits and corresponding events, use if(1<<i)&flag_val_int to perform an AND operation on the trigger flag bit to determine the trigger position, and then match it with the dictionary key to output and temporarily store the corresponding trigger event, forming a complete DataFrame data structure.

[0110] In some implementations, the timestamp before the trigger is extracted using `bisect.bisect(input_df['time'].values,time_index)-1`. The `re.findall()` function, which uses regular expression matching, detects the target ID in the fused data that triggered the algorithm, finding the target information at the time of triggering. Then, `input_df.loc[(input_df['time']==trg_time)` is used to locate the target information before the trigger. The fused data, vehicle chassis power data, and vehicle chassis state data are compared and extracted to form new DataFrame data structures. Here, the target ID can be the ID corresponding to an obstacle, pedestrian, or other target that can trigger an automatic emergency braking event.

[0111] In some implementations, a condition is used to determine if there is trigger information. If not, the system prints that no trigger information was generated, and subsequent parsing is not performed; instead, the report is saved directly.

[0112] In some implementations, the dataframe.concat() function is used to concatenate the extracted algorithm data frame, the perception fusion information data frame, the chassis power-related data frame, the chassis status data frame, the triggering event, the data file name, and the data file ID into a new data frame.

[0113] In some implementations, the problematic data is skipped and the error message is printed by using a try...except... structure in all data loop traversal processing. pd.DataFrame(data={'filename':[filename],'event':['data file error!!!']}).

[0114] In some implementations, a CSV report file is output via DataFrame.to_csv(csv_dir, index=False, header=True), where Linux operating systems use UTF-8 encoding and Windows operating systems use GBK encoding.

[0115] In this embodiment, the driving data of the target vehicle is matched and filtered based on preset topic information. Then, based on the time stamp of the automatic emergency braking event triggered in shadow mode, key information including chassis status data, chassis power data, automatic emergency braking event algorithm data, and perception fusion data is obtained. The above data is synthesized to generate a report, which can filter and fuse highly relevant data during automatic emergency braking testing, thereby realizing customized data analysis and improving the efficiency of processing and analyzing large amounts of data.

[0116] Figure 4 This is a schematic diagram of the composition structure of a driving data processing device provided in this embodiment, as shown below. Figure 4 As shown, the driving data processing device 410 includes: an acquisition module 411, a first determination module 412, and a second determination module 413, wherein:

[0117] The acquisition module 411 is used to acquire at least one first data packet determined from the driving data of the target vehicle, and identification information of each first data packet;

[0118] The first determining module 412 is used to determine, from at least one first data packet, at least one second data packet whose identification information satisfies a first preset condition;

[0119] The second determining module 413 is used to parse at least one of the second data packets to obtain the event triggering information of the target vehicle in shadow mode.

[0120] In some embodiments, the driving data of the target vehicle includes at least one data file, and the identification information includes topic information; the acquisition module is further configured to: acquire a third data packet corresponding to each of the data files from the message queue; wherein each of the third data packets is obtained by encoding the data file; and decode each of the third data packets to obtain at least one first data packet and topic information of each first data packet.

[0121] In some embodiments, each of the second data packets has identification information and a timestamp. The event triggering information includes the triggering time of the first event triggered by the target vehicle in shadow mode and target information associated with the first event. The second determining module is further configured to: parse each of the second data packets to obtain a first information set corresponding to each of the second data packets; determine the triggering time of the first event triggered by the target vehicle in shadow mode based on the timestamps of the second data packets corresponding to each of the first information sets; and obtain target information associated with the first event from at least one of the first information sets based on the triggering time. The target information includes at least one of the following: vehicle information, algorithm state information of the shadow mode, and perception information that triggered the first event.

[0122] In some embodiments, each of the first information sets includes at least trigger flag information, and the trigger flag information in each of the first information sets is used to characterize whether the first event is triggered at the time indicated by the timestamp of the second data packet corresponding to the first information set; the driving data processing device further includes a second determining module, which is further configured to: determine a second information set from at least one of the first information sets; the trigger flag information in the second information set is a first flag value, the first flag value characterizing that the first event was triggered at the time indicated by the timestamp of the second data packet corresponding to the second information set; and determine the trigger time when the target vehicle triggers the first event in shadow mode based on the timestamp of the second data packet corresponding to the second information set.

[0123] In some embodiments, the driving data processing device further includes a third acquisition module, which is further configured to: when the target information includes algorithm state information of the shadow mode, determine a third information set whose corresponding timestamp matches the trigger time from at least one first information set, and acquire algorithm state information of the shadow mode associated with the first event from the third information set; when the target information includes vehicle information, determine a fourth information set whose corresponding timestamp matches the time before the trigger time from at least one first information set, and acquire vehicle information associated with the first event from the fourth information set; when the target information includes perception information that triggers the first event, determine a fourth information set whose corresponding timestamp matches the time before the trigger time from at least one first information set, and acquire perception information that triggers the first event from the fourth information set.

[0124] In some embodiments, the driving data processing device further includes a reporting module, which is further configured to: generate a data report based on the triggering time of the first event triggered by the target vehicle in shadow mode and the target information associated with the first event.

[0125] The above embodiments are merely preferred embodiments provided to fully illustrate this application, and the scope of protection of this application is not limited thereto. Equivalent substitutions or modifications made by those skilled in the art based on this application are all within the scope of protection of this application.

[0126] The descriptions of the apparatus embodiments above are similar to those of the method embodiments above, and have similar beneficial effects. In some embodiments, the functions or modules included in the apparatus provided in this disclosure can be used to perform the methods described in the method embodiments above. For technical details not disclosed in the apparatus embodiments of this application, please refer to the descriptions of the method embodiments of this application for understanding.

[0127] If the technical solution of this application involves personal information, the product using this technical solution has clearly informed the user of the personal information processing rules and obtained the user's voluntary consent before processing the personal information. If the technical solution of this application involves sensitive personal information, the product using this technical solution has obtained the user's separate consent before processing the sensitive personal information, and also meets the requirement of "express consent". For example, at personal information collection devices such as cameras, clear and prominent signs are set up to inform users that they have entered the scope of personal information collection and that personal information will be collected. If an individual voluntarily enters the collection scope, it is deemed that they have agreed to the collection of their personal information; or on the personal information processing device, with clear signs / information informing users of the personal information processing rules, authorization is obtained from the user through pop-up information or by asking the user to upload their personal information; wherein, the personal information processing rules may include information such as the personal information processor, the purpose of personal information processing, the processing method, and the types of personal information processed.

[0128] It should be noted that, in the embodiments of this application, if the above-mentioned behavior recognition method or model training method is implemented in the form of a software functional module and sold or used as an independent product, it can also be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the embodiments of this application, or the part that contributes to the related technology, can be embodied in the form of a software product. This software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the methods described in the various embodiments of this application. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, mobile hard drives, read-only memory (ROM), magnetic disks, or optical disks. Thus, the embodiments of this application are not limited to any specific hardware, software, or firmware, or any combination of hardware, software, and firmware.

[0129] This application provides a computer device including a memory and a processor. The memory stores a computer program that can run on the processor. When the processor executes the program, it implements some or all of the steps in the above-described method.

[0130] This application provides a computer-readable storage medium storing a computer program thereon, which, when executed by a processor, implements some or all of the steps in the above-described method. The computer-readable storage medium can be transient or non-transient.

[0131] This application provides a computer program including computer-readable code, wherein when the computer-readable code is executed in a computer device, a processor in the computer device performs some or all of the steps in the above-described method.

[0132] This application provides a computer program product, which includes a non-transitory computer-readable storage medium storing a computer program. When the computer program is read and executed by a computer, it implements some or all of the steps in the above-described method. This computer program product can be implemented specifically through hardware, software, or a combination thereof. In some embodiments, the computer program product is specifically embodied as a computer storage medium; in other embodiments, the computer program product is specifically embodied as a software product, such as a software development kit (SDK), etc.

[0133] It should be noted that the descriptions of the various embodiments above tend to emphasize the differences between them, while their similarities or commonalities can be referred to interchangeably. The descriptions of the above embodiments of the device, storage medium, computer program, and computer program product are similar to the descriptions of the above method embodiments and have similar beneficial effects. For technical details not disclosed in the embodiments of the device, storage medium, computer program, and computer program product of this application, please refer to the descriptions of the method embodiments of this application for understanding.

[0134] It should be noted that, Figure 5 This is a schematic diagram of a hardware entity of a computer device in an embodiment of this application, such as... Figure 5 As shown, the hardware entity of the computer device 500 includes: a processor 501, a communication interface 502, and a memory 503, wherein:

[0135] Processor 501 typically controls the overall operation of computer device 500.

[0136] Communication interface 502 enables computer devices to communicate with other terminals or servers over a network.

[0137] The memory 503 is configured to store instructions and applications executable by the processor 501, and can also cache data to be processed or already processed (e.g., image data, audio data, voice communication data, and video communication data) in the processor 501 and various modules in the computer device 500. It can be implemented using flash memory or random access memory (RAM). Data transfer between the processor 501, the communication interface 502, and the memory 503 can be performed via bus 504.

[0138] It should be understood that the phrase "one embodiment" or "an embodiment" throughout the specification means that a specific feature, structure, or characteristic related to the embodiment is included in at least one embodiment of this application. Therefore, "in one embodiment" or "in an embodiment" appearing throughout the specification does not necessarily refer to the same embodiment. Furthermore, these specific features, structures, or characteristics can be combined in any suitable manner in one or more embodiments. It should be understood that in the various embodiments of this application, the sequence numbers of the above steps / processes do not imply a sequential order of execution; the execution order of each step / process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of this application. The sequence numbers of the above embodiments of this application are merely descriptive and do not represent the superiority or inferiority of the embodiments.

[0139] It should be noted that, in this document, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Unless otherwise specified, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes that element.

[0140] In the several embodiments provided in this application, it should be understood that the disclosed devices and methods can be implemented in other ways. The device embodiments described above are merely illustrative. For example, the division of units is only a logical functional division, and in actual implementation, there may be other division methods, such as: multiple units or components can be combined, or integrated into another system, or some features can be ignored or not executed. In addition, the coupling, direct coupling, or communication connection between the various components shown or discussed can be through some interfaces, and the indirect coupling or communication connection between devices or units can be electrical, mechanical, or other forms.

[0141] The units described above as separate components may or may not be physically separate. The components shown as units may or may not be physical units. They may be located in one place or distributed across multiple network units. Some or all of the units may be selected to achieve the purpose of this embodiment according to actual needs.

[0142] In addition, each functional unit in the various embodiments of this application can be integrated into one processing unit, or each unit can be a separate unit, or two or more units can be integrated into one unit; the integrated unit can be implemented in hardware or in the form of hardware plus software functional units.

[0143] Those skilled in the art will understand that all or part of the steps of the above method embodiments can be implemented by hardware related to program instructions. The aforementioned program can be stored in a computer-readable storage medium. When the program is executed, it performs the steps of the above method embodiments. The aforementioned storage medium includes various media that can store program code, such as mobile storage devices, read-only memory (ROM), magnetic disks, or optical disks.

[0144] Alternatively, if the integrated units described above are implemented as software functional modules and sold or used as independent products, they can also be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this application, in essence or the part that contributes to related technologies, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the methods described in the various embodiments of this application. The aforementioned storage medium includes various media capable of storing program code, such as mobile storage devices, ROM, magnetic disks, or optical disks.

[0145] The above description is merely an embodiment of this application, but the scope of protection of this application is not limited thereto. Any changes 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.

Claims

1. A method for processing driving data, characterized in that, The method includes: Acquire at least one first data packet determined from the driving data of the target vehicle, and identification information for each first data packet; From at least one of the first data packets, determine at least one second data packet whose identification information satisfies a first preset condition; At least one of the second data packets is parsed to obtain the event triggering information of the target vehicle in shadow mode; Each of the second data packets has identification information and a timestamp. The event triggering information includes the triggering time when the target vehicle triggers the first event in shadow mode, and the target information associated with the first event. The step of parsing at least one of the second data packets to obtain the event triggering information of the target vehicle in shadow mode includes: Each of the second data packets is parsed to obtain the first information set corresponding to each of the second data packets; Based on the timestamps of each first information set and the second data packet corresponding to each first information set, the triggering time of the first event triggered by the target vehicle in shadow mode is determined. Based on the triggering time, target information associated with the first event is obtained from at least one of the first information sets; the target information includes at least one of the following: vehicle information, algorithm state information of the shadow mode, and perception information that triggered the first event; The step of obtaining target information associated with the first event from at least one of the first information sets based on the triggering time includes: When the target information includes the algorithm state information of the shadow mode, a third information set whose corresponding timestamp matches the trigger time is determined from at least one of the first information sets, and the algorithm state information of the shadow mode associated with the first event is obtained from the third information set. If the target information includes vehicle information, a fourth information set matching the timestamp of the triggering time is determined from at least one of the first information sets, and vehicle information associated with the first event is obtained from the fourth information set. If the target information includes the perception information that triggers the first event, a fourth information set is determined from at least one of the first information sets that matches the time preceding the triggering time, and the perception information that triggers the first event is obtained from the fourth information set.

2. The method according to claim 1, characterized in that, The driving data of the target vehicle includes at least one data file, and the identification information includes topic information; the step of obtaining at least one first data packet determined from the driving data of the target vehicle, and the identification information of each first data packet, includes: Retrieve the third data packet corresponding to each of the data files from the message queue; wherein each of the third data packets is obtained by encoding the data file. Each of the third data packets is decoded to obtain at least one first data packet and the subject information of each first data packet.

3. The method according to claim 1, characterized in that, Each of the first information sets includes at least trigger flag information, and the trigger flag information in each of the first information sets is used to characterize whether the first event is triggered at the time indicated by the timestamp of the second data packet corresponding to the first information set; Determining the trigger time of the first event triggered by the target vehicle in shadow mode based on the timestamps of each first information set and the second data packets corresponding to each first information set includes: From at least one of the first information sets, a second information set is determined; the triggering flag information in the second information set is a first flag value, the first flag value indicating that the first event was triggered at the time indicated by the timestamp of the second data packet corresponding to the second information set; Based on the timestamp of the second data packet corresponding to the second information set, the triggering time of the first event triggered by the target vehicle in shadow mode is determined.

4. The method according to any one of claims 1 to 3, characterized in that, The first event includes at least one of the following: automatic emergency braking event, automatic emergency steering event, lane departure warning event; and / or, the vehicle information includes at least one of the following: chassis information, vehicle bus information.

5. The method according to any one of claims 1 to 3, characterized in that, The method further includes generating a data report based on the triggering time of the first event triggered by the target vehicle in shadow mode and the target information associated with the first event.

6. A driving data processing device, characterized in that, include: The acquisition module is used to acquire at least one first data packet determined from the driving data of the target vehicle, and identification information of each first data packet; The first determining module is configured to determine, from at least one first data packet, at least one second data packet whose identification information satisfies a first preset condition; The second determining module is used to parse at least one of the second data packets to obtain the event triggering information of the target vehicle in shadow mode; Each of the second data packets has identification information and a timestamp. The event triggering information includes the triggering time when the target vehicle triggers the first event in shadow mode, and the target information associated with the first event. The second determining module is used to parse each of the second data packets to obtain a first information set corresponding to each of the second data packets; Based on the timestamps of each first information set and the second data packets corresponding to each first information set, the triggering time of the target vehicle triggering the first event in shadow mode is determined; based on the triggering time, target information associated with the first event is obtained from at least one of the first information sets; the target information includes at least one of the following: vehicle information, algorithm state information of the shadow mode, and perception information that triggers the first event; The third acquisition module is configured to: when the target information includes the algorithm state information of the shadow mode, determine a third information set whose corresponding timestamp matches the trigger time from at least one of the first information sets, and acquire the algorithm state information of the shadow mode associated with the first event from the third information set; when the target information includes vehicle information, determine a fourth information set whose corresponding timestamp matches the time before the trigger time from at least one of the first information sets, and acquire the vehicle information associated with the first event from the fourth information set; when the target information includes perception information that triggers the first event, determine a fourth information set whose corresponding timestamp matches the time before the trigger time from at least one of the first information sets, and acquire the perception information that triggers the first event from the fourth information set.

7. A computer device comprising a memory and a processor, the memory storing a computer program executable on the processor, characterized in that, When the processor executes the program, it implements the steps of the method according to any one of claims 1 to 5.

8. A computer-readable storage medium having a computer program stored thereon, characterized in that, When executed by a processor, the computer program implements the steps of the method according to any one of claims 1 to 5.

Images