A scene data mining method, device, electronic device and storage medium

Abstract

The present disclosure provides a scene data mining method, device, electronic device and storage medium, which relate to the field of data processing technology, and in particular to the field of vehicle-road collaboration and autonomous driving technology. The specific implementation scheme includes: in response to a data mining instruction for a target traffic scene event, obtaining the event information of the target traffic scene event and the driving data information of the autonomous driving vehicle associated with the target traffic scene event; determining the effective disk drop time corresponding to the target traffic scene event based on the event information and the driving data information; and according to the effective disk drop time, intercepting corresponding data from the disk drop data of the autonomous driving vehicle as the real scene data corresponding to the target traffic scene event. The disclosed scheme can improve the efficiency of traffic scene data mining.

Description

Technical Field

[0001] The present disclosure relates to the field of data processing technology, in particular to the field of vehicle-road collaboration and autonomous driving technology, and specifically to a scene data mining method, device, electronic device, storage medium and computer program product. Background Art

[0002] Vehicle-to-everything (V2X) interconnected technology enables real-time transmission of traffic information between vehicles and between vehicles and traffic facilities. Within the specific implementation of V2X, vehicle-infrastructure collaboration (VIS) is proposed. This technology leverages wireless communications and other technologies to achieve effective coordination between people, vehicles, and the road through real-time information exchange, ensuring traffic safety while improving traffic efficiency. Summary of the Invention

[0003] The present disclosure provides a scene data mining method, apparatus, electronic device, storage medium, and computer program product.

[0004] According to one aspect of the present disclosure, a scenario data mining method is provided, comprising:

[0005] In response to a data mining instruction for a target traffic scene event, obtaining event information of the target traffic scene event and driving data information of the autonomous driving vehicle associated with the target traffic scene event;

[0006] Determine the effective placement time corresponding to the target traffic scene event based on event information and driving data information;

[0007] According to the effective placement time, the corresponding data is intercepted from the placement data of the autonomous driving vehicle as the real scene data corresponding to the target traffic scene event.

[0008] According to one aspect of the present disclosure, a scene data mining device is provided, comprising:

[0009] a data acquisition module, configured to, in response to a data mining instruction for a target traffic scene event, acquire event information of the target traffic scene event and driving data information of the autonomous driving vehicle associated with the target traffic scene event;

[0010] The effective time determination module is used to determine the effective placement time corresponding to the target traffic scene event based on event information and driving data information;

[0011] The data interception module is used to intercept the corresponding data from the disk data of the autonomous driving vehicle according to the effective disk placement time as the real scene data corresponding to the target traffic scene event.

[0012] According to another aspect of the present disclosure, there is provided an electronic device, comprising:

[0013] at least one processor; and

[0014] a memory communicatively connected to at least one processor; wherein,

[0015] The memory stores instructions that can be executed by at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to execute the scene data mining method of any embodiment of the present disclosure.

[0016] According to another aspect of the present disclosure, a non-transitory computer-readable storage medium storing computer instructions is provided, where the computer instructions are used to enable a computer to execute the scenario data mining method of any embodiment of the present disclosure.

[0017] According to another aspect of the present disclosure, a computer program product is provided, including a computer program, which implements the scenario data mining method of any embodiment of the present disclosure when executed by a processor.

[0018] According to the technology disclosed in the present invention, the efficiency of traffic scene data mining can be improved.

[0019] It should be understood that the contents described in this section are not intended to identify the key or important features of the embodiments of the present disclosure, nor are they intended to limit the scope of the present disclosure. Other features of the present disclosure will become readily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] The accompanying drawings are used to better understand the present invention and do not constitute a limitation of the present invention.

[0021] Figure 1 This is a flow chart of a scenario data mining method provided by an embodiment of the present disclosure;

[0022] Figure 2 This is a flow chart of another scenario data mining method provided by an embodiment of the present disclosure;

[0023] Figure 3 This is a flow chart of another scenario data mining method provided by an embodiment of the present disclosure;

[0024] Figure 4 This is a flow chart of another scenario data mining method provided by an embodiment of the present disclosure;

[0025] Figure 5 is a structural diagram of a scene data mining device provided by an embodiment of the present disclosure;

[0026] Figure 6 It is a block diagram of an electronic device used to implement the scene data mining method of the embodiment of the present disclosure. DETAILED DESCRIPTION

[0027] The following description of exemplary embodiments of the present disclosure is made in conjunction with the accompanying drawings, including various details of the embodiments of the present disclosure to facilitate understanding. These details should be considered as merely exemplary. Therefore, those skilled in the art will recognize that various changes and modifications may be made to the embodiments described herein without departing from the scope and spirit of the present disclosure. Similarly, for the sake of clarity and conciseness, descriptions of well-known functions and structures are omitted in the following description.

[0028] In the disclosed solution, a roadside perception system is deployed in the vehicle-road cooperative area. The system can be composed of roadside perception devices deployed at each intersection. The perception algorithm of vehicle-road cooperation is deployed and run in the roadside perception system. That is, the disclosed solution is carried out in the online or grayscale stage of the perception algorithm. Through the scene detection function of the perception algorithm, the roadside perception system can detect traffic scene events occurring at each intersection and report the detected event information to the cloud. Due to the storage limitations of the roadside perception system, the roadside perception system does not store all the collected real-time data of the intersection. Therefore, the disclosed solution proposes to trigger the roadside perception system to store data on the disk by an autonomous driving vehicle, thereby obtaining the data stored on the disk by the autonomous driving vehicle at each intersection, wherein the stored data can include the collected image data of the intersection and the recognition result data of the image (such as the number of vehicles in the identified intersection, speed, etc.). Specifically, for each intersection in the vehicle-road cooperative area, the intersection perception range is pre-defined. For example, the intersection perception range can be a circular area with the center of the intersection as the origin and a preset distance as the radius. The roadside perception system and the autonomous vehicle can exchange data and communicate with each other, thereby obtaining the real-time location information of the autonomous vehicle. When the autonomous vehicle enters the perception range of the intersection, the corresponding data starts to be recorded, and when the autonomous vehicle leaves the perception range of the intersection, the data recording stops. It should be noted that in order to ensure the accuracy and adequacy of the recorded data, the recorded data for each intersection passed by the autonomous vehicle can also include data from 1 minute before entering the perception range of the intersection + data during the entry + data from 1 minute after leaving the perception range of the intersection. In addition, the roadside perception system will also record and record the driving data of the autonomous vehicle, such as the time of entering and leaving each intersection. On this basis, the process of the scene data mining method can be seen in the following embodiment.

[0029] Figure 1 This is a flowchart of a scenario data mining method according to an embodiment of the present disclosure. This embodiment is applicable to data mining of traffic scene events in vehicle-road collaboration scenarios. The method can be performed by a scenario data mining device implemented in software and / or hardware and integrated into an electronic device.

[0030] For details, see Figure 1 , the scene data mining method is as follows:

[0031] S101. In response to a data mining instruction for a target traffic scene event, obtain event information of the target traffic scene event and driving data information of the autonomous driving vehicle associated with the target traffic scene event.

[0032] The target traffic scene event can be any specified type of traffic scene event. For example, the target traffic scene event can be a vehicle wrong-way event, a vehicle speeding event, a road-occupying event, or an event of driving in a non-prescribed lane. In response to the data mining instruction for the target traffic scene event, the event information of the target traffic scene event can be obtained from the traffic scene event detection results reported to the cloud by the roadside perception system, wherein the event information at least includes the intersection identification, event type, and event start and end time, etc. During the period when the autonomous driving vehicle enters the perception range of a certain intersection, if a target traffic scene event occurs at the intersection, the driving data information of the autonomous driving vehicle at the intersection (such as the time of entering / exiting the intersection) is used as the driving data information associated with the target traffic scene event. In addition, the disk data of the autonomous driving vehicle at the intersection can also be used as the disk data associated with the target traffic scene event. It should be noted here that the association between the target traffic scene event and the driving data information of the autonomous driving vehicle, or the association between the autonomous driving vehicle's landing data at the intersection and the target traffic scene event, can be determined and stored through data preprocessing. Therefore, in this step, the data associated with the target traffic scene event can be directly obtained from the data preprocessing results.

[0033] S102: Determine the effective placement time corresponding to the target traffic scene event based on the event information and driving data information.

[0034] In the disclosed embodiments, the target traffic scene event occurring at the target intersection is used as an example for explanation. There are several situations for the timing of the target traffic scene event: (1) The target traffic scene event may occur before the autonomous driving vehicle enters the perception range of the target intersection and ends while the autonomous driving vehicle enters the perception range of the target intersection. (2) The target traffic scene event may occur after the autonomous driving vehicle enters the perception range of the target intersection and ends before the autonomous driving vehicle leaves the perception range of the target intersection, that is, the target traffic scene event occurs and ends while the autonomous driving vehicle enters the perception range of the target intersection. (3) The target traffic scene event may occur after the autonomous driving vehicle enters the perception range of the target intersection and ends after the autonomous driving vehicle leaves the perception range of the target intersection.

[0035] Since the data written to disk by the autonomous vehicle at each intersection is the data written to disk during the autonomous vehicle's entry into each intersection, in the aforementioned situations, the data written to disk by the autonomous vehicle at the intersection where the target traffic scene event occurred will inevitably contain invalid scene data unrelated to the target traffic scene event. Therefore, it is necessary to filter the data written to disk by the autonomous vehicle at that intersection. It should be noted that if the target traffic scene event occurs before the autonomous vehicle enters the perception range of the target intersection and ends after the autonomous vehicle leaves the perception range of the target intersection, the data written to disk by the autonomous vehicle at that intersection can be directly used as the actual scene data of the target traffic scene event.

[0036] To perform data screening, it is necessary to determine the effective disk drop time corresponding to the target traffic scene event, wherein the effective disk drop time refers to the time when the data of the autonomous driving vehicle is dropped to disk during the stage when the target traffic scene event occurs. Optionally, the effective disk drop time can be determined based on the event information of the target traffic scene event (such as the start and end time of the event) and the driving data of the autonomous driving vehicle at the intersection where the target traffic scene event occurs (such as the time of entering and leaving the intersection). For example, the target traffic scene event occurs at 10:00:00 and ends at 10:10:00; and the driving data associated with the target traffic scene event is: the autonomous driving vehicle enters the intersection where the target traffic scene event occurs at 10:05:00 and leaves at 10:12:00. The time for storing data for the autonomous vehicle at the intersection can be 10:05:00-10:12:00; and the time for storing data for the autonomous vehicle during the target traffic scenario event is 10:05:00-10:10:00, that is, 10:05:00-10:10:00 is the effective storage time.

[0037] It should be noted that different types of traffic scene events have different requirements for the duration of scene data. Therefore, after determining the effective disk placement time, it can be determined whether the duration corresponding to the effective disk placement time meets the requirements. If so, execute S103, otherwise end.

[0038] S103. According to the effective placement time, corresponding data is intercepted from the placement data of the autonomous driving vehicle as real scene data corresponding to the target traffic scene event.

[0039] After obtaining the effective disk placement time through S102, the data of the same time period is directly intercepted from the disk placement data of the autonomous driving vehicle and used as the real scene data corresponding to the target traffic scene event.

[0040] In the embodiment of the present disclosure, there is no need to manually construct traffic scenes. The real scene data corresponding to different traffic scene events can be directly mined from the disk data. This not only improves the efficiency of obtaining scene data, but also the present disclosure solution is not restricted by intersection traffic and geographical restrictions.

[0041] Figure 2 FIG. 1 is a flow chart of another scenario data mining method according to an embodiment of the present disclosure. Figure 2 ,The scene data mining method is as follows:

[0042] S201. In response to a data mining instruction for a target traffic scene event, obtain event information of the target traffic scene event and driving data information of the autonomous driving vehicle associated with the target traffic scene event.

[0043] Among them, the event information of the target traffic scene event may include the start and end time of the event and the location of the intersection where the event occurred; the driving data information of the autonomous driving vehicle associated with the target traffic scene event may include the driving time of the autonomous driving vehicle at the intersection where the target traffic scene event occurs, such as the time when the vehicle enters and leaves the intersection.

[0044] S202: Determine the positional relationship between the event start and end time in the event information and the vehicle travel time in the travel data information.

[0045] Among them, the positional relationship between the event start and end time and the vehicle travel time can include the following three types: (1) The event start time is earlier than the vehicle's entry time, and the event end time is after the entry time and before the exit time, that is, the target traffic scene event occurs before the autonomous driving vehicle enters the perception range of the intersection and ends during the period when the autonomous driving vehicle enters the perception range of the intersection. (2) The time start and end time are within the time range of the vehicle entering and leaving the intersection, that is, the target traffic scene event occurs and ends during the period when the autonomous driving vehicle enters the perception range of the intersection. (3) The event start time is after the entry time and before the exit time, and the event end time is later than the vehicle exit time, that is, the target traffic scene event occurs after the autonomous driving vehicle enters the perception range of the target intersection and ends after the autonomous driving vehicle leaves the perception range of the target intersection.

[0046] S203: Determine the effective placement time corresponding to the target traffic scene event based on the position relationship.

[0047] In an optional embodiment, based on the location relationship, if it is determined that there is an intersection between the event start and end times and the vehicle travel time, the intersecting time segment is used as the effective disk drop time corresponding to the target traffic scene event. This intersection operation can quickly and accurately determine the effective disk drop time, providing a guarantee for efficient scene data mining. For example, the target traffic scene event occurs at 10:00:00 and ends at 10:10:00; and the driving data associated with the target traffic scene event is: the autonomous driving vehicle enters the intersection where the target traffic scene event occurs at 10:05:00 and leaves at 10:12:00. The disk drop time of the autonomous driving vehicle's data at this intersection can be 10:05:00-10:12:00; and the time for the autonomous driving vehicle to drop data to disk during the target traffic scene event is 10:05:00-10:10:00, that is, 10:05:00-10:10:00 is the effective disk drop time.

[0048] S204. According to the effective placement time, corresponding data is intercepted from the placement data of the autonomous driving vehicle as real scene data corresponding to the target traffic scene event.

[0049] After obtaining the effective disk placement time through S203, the data of the same time period is directly intercepted from the disk placement data of the autonomous driving vehicle and used as the real scene data corresponding to the target traffic scene event.

[0050] In the disclosed embodiment, the effective landing time can be accurately determined through the position relationship between the start and end time of the event and the vehicle driving time, providing a guarantee for efficient mining of scene data; and the overall solution does not require manual construction of traffic scenes, and can directly mine real scene data corresponding to different traffic scene events from the landing data, so that the mining of scene data not only improves the efficiency of scene data acquisition, but also the solution is not restricted by intersection traffic and geographical restrictions.

[0051] Furthermore, the disclosed solution also requires attention to the event generation time in the event information. The event generation time refers to the period from the moment a certain type of scene occurs at an intersection to the time the roadside perception algorithm identifies and determines the event. For example, a scene such as a lane-blocking vehicle must remain stationary for a certain period of time to be considered a lane-blocking vehicle event. This time is important because most roadside data is generated based on vehicle entry and exit. If a certain type of traffic scene event takes a long time to generate, and the autonomous vehicle does not pass through the intersection during the generation period, this data will not be recorded, making this data unusable. Therefore, the disclosed solution also obtains the event generation time and then verifies and corrects the positional relationship between the event start and end times in the event information and the vehicle travel time in the driving data information based on the event generation time. Optionally, for the first and second positional relationships, the event start time is shifted forward by a certain amount of time to obtain a new event start time, where the certain amount of time is equal to the event generation time. The two positional relationships are then verified and corrected based on the new event start time, and the effective recording time is determined based on the new positional relationship. Similarly, for the third position relationship, the event deadline is shifted back a certain amount of time to obtain a new event deadline, where the certain amount of time is equal to the event generation time. This position relationship is then verified and corrected based on the new event deadline, and the effective disk placement time is determined based on the new position relationship.

[0052] For example, without considering the event generation time, it is identified that the target traffic scene event occurs at 10:05:00 and ends at 10:10:00; the driving data associated with the target traffic scene event is: the autonomous driving vehicle enters the intersection where the target traffic scene event occurs at 10:00:00 and leaves at 10:12:00, then the effective drop-off time is determined to be 10:05:00-10:12:00. In the case of considering the event generation time, if the event generation time is 1 minute, the new event start time is 10:04:00; then the newly determined effective drop-off time is 10:04:00-10:10:00. In this way, the drop-off data within the event generation time is incorporated into the corresponding scene data, making the final obtained real scene data more accurate.

[0053] Figure 3 FIG. 1 is a flow chart of another scenario data mining method according to an embodiment of the present disclosure. Figure 3 ,The scene data mining method is as follows:

[0054] S301. Obtain event information of traffic scene events occurring at each intersection within the vehicle-road cooperative area.

[0055] In the disclosed embodiment, the roadside perception system reports relevant information of traffic scene events occurring in the vehicle-road cooperative area to the cloud storage in real time, thereby directly obtaining event information of traffic scene events occurring at various intersections in the vehicle-road cooperative area from the cloud. The event information may include the start and end time of the event, the event type, the identifier of the intersection location where the event occurred (such as the intersection number), and the time when the event was generated.

[0056] S302. Obtain driving data information of the autonomous driving vehicle when passing through each intersection in the vehicle-road cooperative area.

[0057] In the disclosed embodiments, the roadside perception system can communicate and interact with the autonomous vehicle to obtain driving data information from the autonomous vehicle as it passes through each intersection within the V2X area, and store the data on disk. This data can be directly retrieved from the autonomous vehicle's stored data. This driving data information can include the intersection number of each intersection passed by the autonomous vehicle, as well as the time it entered and exited each intersection.

[0058] S303: Align the event information with the driving data information according to preset parameters to determine the correlation between the traffic scene event and the driving data information.

[0059] Among them, the preset parameters can be selected as intersection numbers, event times, etc. During the alignment process, for event information and driving data information with the same road number, it is determined whether there is an intersection between the event start and end times and the entry and exit times of the autonomous vehicle. If so, an association relationship is established between the traffic scene event and the driving data information of the autonomous vehicle. If there is no intersection, it indicates that the autonomous vehicle did not enter the intersection during the traffic scene event phase at the intersection, or had already left the intersection before the event occurred. In this case, there is no need to establish an association relationship between the traffic scene event and the driving data information.

[0060] It should be noted here that, during the stage when a traffic scene event occurs, if multiple autonomous driving vehicles successively pass through the intersection where the traffic scene event occurs, the driving data of each autonomous driving vehicle is aggregated to obtain the final driving data.

[0061] S304: Obtain the time point information of the disk data of the autonomous driving vehicle.

[0062] S305: Align the event start and end times in the event information with the disk transfer time point information to determine the disk transfer data associated with the traffic scene event.

[0063] Because autonomous vehicles trigger data flushing at every intersection, the flushing time is recorded simultaneously. This information is the start and end times of the data flushed to disk at each intersection. After obtaining the flushing time corresponding to the autonomous vehicle's flushed data, the event start and end times in the event information are aligned with the flushing time. If the two times intersect, the association between the traffic event and the flushed data corresponding to the flushing time is determined. If the two times do not intersect, the flushed data corresponding to the flushing time is determined to be redundant, indicating that no traffic event occurred when the autonomous vehicle passed through the intersection.

[0064] In this way, through steps S301-S305, data preprocessing is achieved, providing data preparation for subsequent scene data mining.

[0065] S306. In response to a data mining instruction for a target traffic scene event, obtain event information of the target traffic scene event and driving data information of the autonomous driving vehicle associated with the target traffic scene event.

[0066] S307: Determine the effective placement time corresponding to the target traffic scene event based on the event information and driving data information.

[0067] S308. According to the effective placement time, corresponding data is intercepted from the placement data of the autonomous driving vehicle as real scene data corresponding to the target traffic scene event.

[0068] In the disclosed embodiment, through the above-mentioned data alignment processing, the autonomous driving vehicle driving data and disk data associated with each traffic scene event can be accurately determined, providing a guarantee for subsequent scene data mining.

[0069] Figure 4 FIG. 1 is a flow chart of another scenario data mining method according to an embodiment of the present disclosure. Figure 4 ,The scene data mining method is as follows:

[0070] S401. In response to a data mining instruction for a target traffic scene event, obtain event information of the target traffic scene event and driving data information of the autonomous driving vehicle associated with the target traffic scene event.

[0071] S402: Determine the effective placement time corresponding to the target traffic scene event based on the event information and driving data information.

[0072] S403. According to the effective placement time, corresponding data is intercepted from the placement data of the autonomous driving vehicle as real scene data corresponding to the target traffic scene event.

[0073] S404: Frame extraction and transcoding are performed on the real scene data to generate corresponding event video data, so that the target traffic scene event can be verified based on the event video data.

[0074] In the disclosed embodiment, the intercepted real scene data can be the code stream (e.g., h264 code stream) data transmitted by each roadside camera. The intercepted code stream data can be first subjected to frame extraction processing to avoid excessive code stream data volume causing a large consumption of resources of the scene data mining equipment. Then, the code stream after frame extraction processing can be converted into video data using a transcoding tool. The identified target traffic scene event can then be verified based on the video data. If the verification result is true, the mined real scene data is used as valid data and can be used for subsequent offline algorithm verification. If the verification result is false, it is determined that the perception algorithm of the roadside system has recognized an error. The verification results can be statistically analyzed to determine the recognition accuracy of the roadside perception algorithm. In addition, if the verification result is too true, it can also be judged based on the video data whether the mined scene data meets the requirement specifications.

[0075] In the disclosed embodiment, video data is obtained by frame extraction and transcoding, thereby ensuring that target traffic events can be verified based on the video data, thereby achieving the purpose of evaluating traffic scene events.

[0076] Figure 5 This is a schematic diagram of the structure of the scene data mining device according to an embodiment of the present disclosure. This embodiment is applicable to the case of performing data mining on traffic scene events in a vehicle-road cooperative scenario. Figure 5 ,include:

[0077] A data acquisition module 501 is configured to, in response to a data mining instruction for a target traffic scene event, acquire event information of the target traffic scene event and driving data information of the autonomous driving vehicle associated with the target traffic scene event;

[0078] The effective time determination module 502 is used to determine the effective placement time corresponding to the target traffic scene event based on the event information and driving data information;

[0079] The data interception module 503 is used to intercept corresponding data from the disk data of the autonomous driving vehicle according to the effective disk placement time as the real scene data corresponding to the target traffic scene event.

[0080] Based on the above embodiment, optionally, the effective time determination module includes:

[0081] a relationship determination unit, configured to determine a positional relationship between the event start and end times in the event information and the vehicle travel time in the travel data information;

[0082] The time determination unit is used to determine the effective placement time corresponding to the target traffic scene event based on the position relationship.

[0083] Based on the above embodiment, optionally, the time determination unit is further configured to:

[0084] Based on the location relationship, if it is determined that there is an intersection between the start and end time of the event and the vehicle travel time, the intersecting time segment will be used as the effective placement time corresponding to the target traffic scene event.

[0085] Based on the above embodiment, optionally, the event information also includes the event generation time;

[0086] Accordingly, the device further comprises:

[0087] The verification module is used to verify and correct the position relationship according to the event generation time.

[0088] Based on the above embodiment, optionally, the method further includes:

[0089] The first acquisition module is used to obtain event information of traffic scene events occurring at each intersection in the vehicle-road cooperative area;

[0090] The second acquisition module is used to obtain driving data information of the autonomous driving vehicle when passing through each intersection in the vehicle-road cooperative area;

[0091] The first relationship determination module is used to align the event information and the driving data information according to preset parameters to determine the correlation relationship between the traffic scene event and the driving data information.

[0092] Based on the above embodiment, optionally, the method further includes:

[0093] The third acquisition module is used to obtain the time point information of the disk data stored by the autonomous driving vehicle;

[0094] The second relationship determination module is used to align the event start and end times in the event information with the disk transfer time point information to determine the disk transfer data associated with the traffic scene event.

[0095] Based on the above embodiment, optionally, the method further includes:

[0096] The transcoding module is used to extract frames and transcode real scene data to generate corresponding event video data, so that traffic scene events can be verified based on the event video data.

[0097] The scene data mining device provided in the embodiment of the present disclosure can execute the scene data mining method provided in any embodiment of the present disclosure, and has the corresponding functional modules and beneficial effects of the execution method. For any content not described in detail in this embodiment, please refer to the description of any method embodiment of the present disclosure.

[0098] In the technical solutions disclosed herein, the acquisition, storage, and application of user personal information involved comply with the provisions of relevant laws and regulations and do not violate public order and good morals.

[0099] According to an embodiment of the present disclosure, the present disclosure also provides an electronic device, a readable storage medium, and a computer program product.

[0100] Figure 6 A schematic block diagram of an example electronic device 600 that can be used to implement embodiments of the present disclosure is shown. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as personal digital assistants, cellular phones, smartphones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions are provided as examples only and are not intended to limit the implementation of the present disclosure described and / or claimed herein.

[0101] like Figure 6 As shown, the device 600 includes a computing unit 601, which can perform various appropriate actions and processes according to a computer program stored in a read-only memory (ROM) 602 or a computer program loaded from a storage unit 608 into a random access memory (RAM) 603. Various programs and data required for the operation of the device 600 can also be stored in the RAM 603. The computing unit 601, the ROM 602, and the RAM 603 are connected to each other via a bus 604. An input / output (I / O) interface 605 is also connected to the bus 604.

[0102] Various components in device 600 are connected to I / O interface 605, including an input unit 606, such as a keyboard, mouse, etc.; an output unit 607, such as various types of displays, speakers, etc.; a storage unit 608, such as a magnetic disk, optical disk, etc.; and a communication unit 609, such as a network card, modem, wireless communication transceiver, etc. The communication unit 609 allows device 600 to exchange information / data with other devices via a computer network such as the Internet and / or various telecommunication networks.

[0103] The computing unit 601 can be a variety of general-purpose and / or specialized processing components with processing and computing capabilities. Some examples of the computing unit 601 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various dedicated artificial intelligence (AI) computing chips, various computing units that run machine learning model algorithms, digital signal processors (DSPs), and any appropriate processors, controllers, microcontrollers, etc. The computing unit 601 performs the various methods and processes described above, such as the scene data mining method. For example, in some embodiments, the scene data mining method can be implemented as a computer software program that is tangibly contained in a machine-readable medium, such as the storage unit 608. In some embodiments, part or all of the computer program can be loaded and / or installed on the device 600 via the ROM 602 and / or the communication unit 609. When the computer program is loaded into the RAM 603 and executed by the computing unit 601, one or more steps of the scene data mining method described above can be performed. Alternatively, in other embodiments, the computing unit 601 can be configured to perform the scene data mining method by any other appropriate means (e.g., by means of firmware).

[0104] Various embodiments of the systems and techniques described above can be implemented in digital electronic circuit systems, integrated circuit systems, field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), system-on-chip systems (SOCs), complex programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various embodiments can include being implemented in one or more computer programs that are executable and / or interpreted on a programmable system that includes at least one programmable processor, which can be a special purpose or general purpose programmable processor that can receive data and instructions from a storage system, at least one input device, and at least one output device, and transmit data and instructions to the storage system, the at least one input device, and the at least one output device.

[0105] The program code for implementing the method of the present disclosure can be written in any combination of one or more programming languages. These program codes can be provided to a processor or controller of a general-purpose computer, a special-purpose computer, or other programmable data processing device so that when the program code is executed by the processor or controller, the functions / operations specified in the flow chart and / or block diagram are implemented. The program code can be executed entirely on the machine, partially on the machine, as a stand-alone software package, partially on the machine and partially on a remote machine, or entirely on a remote machine or server.

[0106] In the context of the present disclosure, a machine-readable medium can be a tangible medium that can contain or store a program for use by or in conjunction with an instruction execution system, device or equipment. A machine-readable medium can be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium can include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or equipment, or any suitable combination of the foregoing. A more specific example of a machine-readable storage medium can include an electrical connection based on one or more lines, a portable computer disk, 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 foregoing.

[0107] To provide interaction with a user, the systems and techniques described herein can be implemented on a computer having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and pointing device (e.g., a mouse or trackball) through which the user can provide input to the computer. Other types of devices can also be used to provide interaction with the user; for example, the feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including acoustic input, voice input, or tactile input).

[0108] The systems and techniques described herein can be implemented in a computing system that includes back-end components (e.g., as a data server), or a computing system that includes middleware components (e.g., an application server), or a computing system that includes front-end components (e.g., a user computer having a graphical user interface or a web browser through which a user can interact with implementations of the systems and techniques described herein), or a computing system that includes any combination of such back-end components, middleware components, or front-end components. The components of the system can be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include a local area network (LAN), a wide area network (WAN), and the Internet.

[0109] A computer system may include a client and a server. The client and server are generally remote from each other and typically interact through a communication network. The client-server relationship arises through computer programs running on the respective computers and having a client-server relationship with each other. The server may be a cloud server, a server in a distributed system, or a server integrated with a blockchain.

[0110] It should be understood that the various forms of the processes shown above can be used to reorder, add, or delete steps. For example, the steps described in this disclosure can be performed in parallel, sequentially, or in a different order, as long as the desired results of the technical solutions disclosed in this disclosure can be achieved. This is not a limitation herein.

[0111] The above specific embodiments do not constitute a limitation on the scope of protection of this disclosure. Those skilled in the art will appreciate that various modifications, combinations, sub-combinations, and substitutions may be made based on design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of this disclosure shall be included within the scope of protection of this disclosure.

Claims

1. A scene data mining method, comprising: In response to a data mining instruction for a target traffic scene event, acquiring event information of the target traffic scene event and driving data information of the autonomous driving vehicle associated with the target traffic scene event; Determine the positional relationship between the event start and end times in the event information and the vehicle travel time in the travel data information; based on the positional relationship, if it is determined that there is an intersection between the event start and end times and the vehicle travel time, then use the intersecting time segment as the effective disk download time corresponding to the target traffic scene event; wherein the effective disk download time refers to the time when the autonomous driving vehicle data is downloaded to the disk during the target traffic scene event occurrence stage; the positional relationship includes: the event start time is earlier than the vehicle's entry time into the intersection, and the event end time is after the entry time into the intersection and before the exit time from the intersection; or, the time start and end time are within the time range of the vehicle entering and leaving the intersection; or, the event start time is after the entry time into the intersection and before the exit time from the intersection, and the event end time is later than the vehicle's exit time. According to the effective disk placement time, corresponding data is intercepted from the disk placement data of the autonomous driving vehicle as real scene data corresponding to the target traffic scene event.

2. The method according to claim 1, wherein The event information also includes the event generation time; Accordingly, the method further includes: The position relationship is verified and corrected according to the event generation time.

3. The method according to claim 1, further comprising: Obtain event information of traffic scene events occurring at each intersection in the vehicle-road cooperative area; Obtaining driving data information of the autonomous driving vehicle when passing through each intersection in the vehicle-road cooperative area; The event information and the driving data information are aligned according to preset parameters to determine the correlation relationship between the traffic scene event and the driving data information.

4. The method according to claim 3, further comprising: Obtaining the time point information of the disk data stored by the autonomous driving vehicle; The event start and end times in the event information are aligned with the disk transfer time point information to determine the disk transfer data associated with the traffic scene event.

5. The method according to claim 1, further comprising: The real scene data is subjected to frame extraction and transcoding processing to generate corresponding event video data, so that the traffic scene event can be verified based on the event video data.

6. A scene data mining device, comprising: a data acquisition module, configured to, in response to a data mining instruction for a target traffic scene event, acquire event information of the target traffic scene event and driving data information of the autonomous driving vehicle associated with the target traffic scene event; An effective time determination module, configured to determine an effective disk placement time corresponding to the target traffic scene event based on the event information and the driving data information; The effective disk storage time refers to the time when the autonomous driving vehicle data is stored during the target traffic scenario event phase. a data interception module, configured to intercept corresponding data from the disk data of the autonomous driving vehicle according to the effective disk download time as real scene data corresponding to the target traffic scene event; Wherein, the effective time determination module includes: a relationship determination unit, configured to determine a positional relationship between the event start and end times in the event information and the vehicle travel time in the travel data information; the positional relationship including: the event start time is earlier than the time when the vehicle enters the intersection, and the event end time is after the time when the vehicle enters the intersection and before the time when the vehicle leaves the intersection; or, the event start and end times are within the time range of the vehicle entering and leaving the intersection; or, the event start time is after the time when the vehicle enters the intersection and before the time when the vehicle leaves the intersection, and the event end time is later than the time when the vehicle leaves the intersection; a time determination unit, configured to determine, based on the position relationship, an effective placement time corresponding to the target traffic scene event; The time determination unit is further configured to: According to the positional relationship, if it is determined that there is an intersection between the start and end times of the event and the vehicle travel time, the intersecting time segment is used as the effective placement time corresponding to the target traffic scene event.

7. The device according to claim 6, wherein The event information also includes the event generation time; Accordingly, the device further includes: The verification module is used to verify and correct the position relationship according to the event generation time.

8. The apparatus according to claim 6, further comprising: The first acquisition module is used to obtain event information of traffic scene events occurring at each intersection in the vehicle-road cooperative area; The second acquisition module is used to obtain driving data information of the autonomous driving vehicle when passing through each intersection in the vehicle-road cooperative area; The first relationship determination module is used to align the event information with the driving data information according to preset parameters to determine the association relationship between the traffic scene event and the driving data information.

9. The apparatus according to claim 8, further comprising: A third acquisition module is used to obtain the time point information of the disk data stored by the autonomous driving vehicle; The second relationship determination module is configured to align the event start and end times in the event information with the disk transfer time point information to determine the disk transfer data associated with the traffic scene event.

10. The apparatus according to claim 6, further comprising: The transcoding module is used to perform frame extraction and transcoding processing on the real scene data to generate corresponding event video data, so that the traffic scene event can be verified based on the event video data.

11. An electronic device comprising: at least one processor; as well as a memory communicatively connected to the at least one processor; wherein, The memory stores instructions that can be executed 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 method according to any one of claims 1 to 5.

12. A non-transitory computer-readable storage medium storing computer instructions, wherein: The computer instructions are used to cause the computer to execute the method according to any one of claims 1 to 5.

13. A computer program product comprising a computer program, which, when executed by a processor, implements the method according to any one of claims 1 to 5.

Images