Data processing method, device, equipment, storage medium and product

Abstract

The present application discloses a data processing method, device, equipment, storage medium and product, which relates to the field of intelligent driving technology. The method includes: obtaining intelligent driving data; identifying the driving state of each frame in the intelligent driving data; calculating the proportion of the corresponding driving state in the intelligent driving data according to the driving state of each frame in the intelligent driving data; determining the driving state of the current scene according to the proportion of the driving state, and obtaining the corresponding driving data based on the driving state of the current scene. This solution determines the driving state of the current vehicle driving scene by the proportion of different driving states, which can improve the overall performance of the intelligent driving system, and can also be optimized for specific application scenarios. By distinguishing the driving data corresponding to different driving states, it effectively promotes the optimization of the intelligent driving data set, thereby realizing more efficient and accurate training and iteration of the intelligent driving algorithm.

Description

Technical Field

[0001] The present application relates to the field of intelligent driving technology, and in particular to data processing methods, devices, equipment, storage media and products. Background Art

[0002] For data on different driving states, due to their different functions, the data processing methods for different driving states are different when the intelligent driving prediction data set is generated. For example, there are big differences in the processing processes such as map topology construction, vehicle lane binding, and vehicle lane change recognition. For different usage scenarios, it is also necessary to identify the driving state of the data set. For example, when training the driving trajectory planning model, it is necessary to use the human driving state data for training.

[0003] Therefore, distinguishing the driving states of the intelligent driving dataset is an important issue in dataset construction. Summary of the invention

[0004] The main purpose of this application is to provide a data processing method, device, equipment, storage medium and product, aiming to solve the technical problem of how to distinguish the driving data corresponding to the driving status of the intelligent driving data set.

[0005] To achieve the above objectives, the present application proposes a data processing method, which includes:

[0006] Acquire intelligent driving data;

[0007] Identifying the driving status of each frame in the intelligent driving data;

[0008] According to the driving state of each frame in the intelligent driving data, calculating the proportion of the driving state corresponding to the intelligent driving data;

[0009] According to the proportion of the driving status, the driving status of the current scene is determined, and corresponding driving data is obtained based on the driving status of the current scene.

[0010] In one embodiment, the step of identifying the driving state of each frame in the intelligent driving data includes:

[0011] Based on a predefined state set and / or a vehicle operation state set, the driving state of each frame in the intelligent driving data is identified.

[0012] In one embodiment, the driving state includes an intelligent driving state NZP state based on a high-precision map, an intelligent driving state LCC based on a perception map, an ACC state based on an adaptive cruise system, and a human driving state, the predefined state set includes state activation, the predefined vehicle operation state set includes driving, and the step of identifying the driving state of each frame in the intelligent driving data based on the predefined state set and / or the vehicle operation state set includes:

[0013] Determine whether the NZP state of each frame in the intelligent driving data is state activated;

[0014] If the NZP state of each frame in the intelligent driving data is state activated, determining that the driving state corresponding to each frame in the intelligent driving data is the NZP state;

[0015] If the NZP state of each frame in the intelligent driving data is not state activated, determining whether the LCC state of each frame in the intelligent driving data is LCC state activated;

[0016] If the LCC state of each frame in the intelligent driving data is state activated, determining that the driving state corresponding to each frame in the intelligent driving data is the LCC state;

[0017] If the LCC state of each frame in the intelligent driving data is not state activated, determining whether the ACC state of each frame in the intelligent driving data is state activated;

[0018] If the ACC state of each frame in the intelligent driving data is state activated, determining that the driving state corresponding to each frame in the intelligent driving data is the ACC state;

[0019] If the ACC state of each frame in the intelligent driving data is not the activated state, determining whether the human driving state of each frame in the intelligent driving data is driving;

[0020] If the human driving state of each frame in the intelligent driving data is driving, it is determined that the driving state corresponding to each frame in the intelligent driving data is the human driving state.

[0021] In one embodiment, after the step of identifying the driving status of different frames in the intelligent driving data, the method further includes:

[0022] According to the driving state of each frame in the intelligent driving data, a corresponding driving state scene level list is created, wherein the driving state scene level list is used to record the corresponding driving state;

[0023] Determine whether the driving state corresponding to the driving state scene-level list is consistent with the preset driving state;

[0024] If so, marking a first label on the state flag bit of the corresponding driving state in the driving state scene level list;

[0025] According to the driving state of each frame in the intelligent driving data, the step of calculating the proportion of the driving state corresponding to the intelligent driving data comprises:

[0026] Counting the number of driving states in which the state flag bit of the corresponding driving state in the driving state scene-level list is marked with the first label;

[0027] Based on the number of corresponding driving states in the finite frame data segment marked with the first label, the proportion of the corresponding driving states is calculated.

[0028] In one embodiment, the step of calculating the proportion of the corresponding driving states based on the number of driving states marked with the first tag includes:

[0029] Calculate the number of elements from the start frame to the end frame;

[0030] The number of driving states marked with the first label is divided by the number of elements between the start frame and the end frame to obtain the proportion of the corresponding driving state.

[0031] In one embodiment, the step of determining the driving state of the current scene according to the proportion of the driving state, and obtaining corresponding driving data based on the driving state of the current scene includes:

[0032] Compare the proportions of different driving states and obtain the driving state corresponding to the maximum proportion value;

[0033] Comparing the driving state corresponding to the maximum proportion value with a preset threshold;

[0034] If the driving state corresponding to the maximum proportion value is greater than the preset threshold value, determining the driving state corresponding to the maximum proportion value as the driving state of the current scene;

[0035] Based on the driving status of the current scene, corresponding driving data is obtained.

[0036] In addition, to achieve the above-mentioned purpose, the present application also proposes a data processing device, the data processing device comprising:

[0037] An acquisition module, used to acquire intelligent driving data;

[0038] An identification module, used to identify the driving status of each frame in the intelligent driving data;

[0039] A calculation module, used to calculate the proportion of the driving state corresponding to the intelligent driving data according to the driving state of each frame in the intelligent driving data;

[0040] The determination module is used to determine the driving state of the current scene according to the proportion of the driving state, and obtain corresponding driving data based on the driving state of the current scene.

[0041] In addition, to achieve the above objectives, the present application also proposes a data processing device, which includes: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the computer program is configured to implement the steps of the data processing method described above.

[0042] In addition, to achieve the above objectives, the present application also proposes a storage medium, which is a computer-readable storage medium, and a computer program is stored on the storage medium. When the computer program is executed by a processor, the steps of the data processing method described above are implemented.

[0043] In addition, to achieve the above-mentioned purpose, the present application also provides a computer program product, which includes a computer program, and when the computer program is executed by a processor, the steps of the data processing method described above are implemented.

[0044] The present application provides a data processing method, device, equipment, storage medium and product, the method comprising obtaining intelligent driving data; identifying the driving state of each frame in the intelligent driving data; calculating the proportion of the driving state corresponding to the intelligent driving data according to the driving state of each frame in the intelligent driving data; determining the driving state of the current scene according to the proportion of the driving state, and obtaining the corresponding driving data based on the driving state of the current scene. This solution determines the driving state of the current vehicle driving scene by the proportion of different driving states, which can improve the overall performance of the intelligent driving system, and can also be optimized for specific application scenarios, and by distinguishing the driving data corresponding to different driving states, it effectively promotes the optimization of the intelligent driving data set, thereby achieving more efficient and accurate training and iteration of the system algorithm. BRIEF DESCRIPTION OF THE DRAWINGS

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

[0046] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the following is a brief introduction to the drawings required for use in the embodiments or the description of the prior art. Obviously, for ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative labor.

[0047] Figure 1 A flowchart of the first embodiment of the data processing method of the present application is provided;

[0048] Figure 2 This is a schematic diagram of a frame-level driving state determination process involved in the first embodiment of the present application;

[0049] Figure 3 This is a schematic diagram of the NZP state of the valid data segment extracted from the state_NZP_scene_list involved in the first embodiment of the present application;

[0050] Figure 4 A flowchart of the second embodiment of the data processing method of this application is provided;

[0051] Figure 5 This is a schematic diagram of the module structure of the data processing device according to an embodiment of the present application;

[0052] Figure 6 Schematic diagram of the device structure of the hardware operating environment involved in the data processing method in the embodiment of the present application.

[0053] The purpose, features and advantages of this application will be further described in conjunction with the embodiments and with reference to the accompanying drawings. DETAILED DESCRIPTION

[0054] It should be understood that the specific embodiments described herein are only used to explain the technical solutions of the present application and are not used to limit the present application.

[0055] In order to better understand the technical solution of the present application, a detailed description will be given below in conjunction with the accompanying drawings and specific implementation methods.

[0056] The main solutions of the embodiments of the present application are: obtaining intelligent driving data; identifying the driving status of different frames in the intelligent driving data; extracting the proportion of driving status in different frames based on the valid frame data fragments in the intelligent driving data; and determining the driving status of the current scene based on the proportion of driving status.

[0057] For different driving states, due to the different functions of the data, the intelligent driving prediction dataset has different data processing methods for different driving states when it is generated. For example, there are large differences in the processing flows such as map topology construction, vehicle lane binding, and vehicle lane change recognition. For different usage scenarios, it is also necessary to identify the driving state of the dataset. For example, when training the driving trajectory planning model, it is necessary to use the human driving state data for training. Therefore, distinguishing the driving state of the intelligent driving dataset is an important issue in dataset construction.

[0058] The present application provides a solution, which collects real-time or historical data from intelligent driving vehicles and extracts key driving status information from the intelligent driving data for subsequent analysis. By evaluating the frequency of occurrence of different driving states, it helps to understand the main behavior patterns of vehicles in a specific time period. Based on the proportion of driving states, the driving state that is most likely to represent the current scene is determined to improve the overall performance of the intelligent driving system. It can also be optimized for specific application scenarios, thereby improving the safety of the system and user experience. By accurately distinguishing and confirming the driving data corresponding to different driving states, more efficient and accurate training and iteration of intelligent driving algorithms are achieved.

[0059] It should be noted that the execution subject of this embodiment may be a computing service device with data processing, network communication and program running functions, such as a tablet computer, a personal computer, a mobile phone, etc., or an electronic device capable of realizing the above functions, a vehicle-mounted system, etc. The following takes a mobile phone as an example to illustrate this embodiment and the following embodiments.

[0060] Based on this, the present application embodiment provides a data processing method, referring to Figure 1 , Figure 1 This is a flowchart of the first embodiment of the data processing method of the present application.

[0061] In this embodiment, the data processing method includes steps S10 to S40:

[0062] Step S10, acquiring intelligent driving data;

[0063] It should be noted that the intelligent driving data set covers a wide range of driving information. These data not only reflect the vehicle's immediate status, but also include information on multiple levels such as environment, perception, and decision-making. According to the different functions and application scenarios of intelligent driving, the intelligent driving driving status can be roughly divided into the following categories: intelligent driving status based on high-precision maps (Navigational Zero Pilot, NZP); intelligent driving status based on perception maps (Lane Centering Control, LCC); driving status based on adaptive cruise system (Adaptive Cruise Control, ACC); human driving status.

[0064] Among them, the intelligent driving state based on high-precision maps refers to a state in which the vehicle relies on high-precision map data to achieve autonomous navigation from point A to point B;

[0065] Intelligent driving state based on perception map, which focuses on center keeping and lane tracking within a single lane. The vehicle uses visual sensors (such as cameras) and radar to detect lane lines and keep the vehicle in the center of the lane.

[0066] The driving state based on the adaptive cruise system allows the vehicle to automatically adjust the speed to maintain a safe distance from the vehicle in front. It is a longitudinal control technology.

[0067] Human driving state means that the driver directly controls the vehicle, but modern vehicles are usually equipped with various auxiliary systems, such as blind spot monitoring, reversing images, emergency brake assist, etc. These systems provide warnings or interventions when necessary to enhance driving safety.

[0068] Step S20, identifying driving states of different frames in the intelligent driving data;

[0069] It should be noted that intelligent driving data is generally composed of a series of "frames" that are continuous in time, and each frame represents the status of the vehicle and information about its surrounding environment at a specific moment.

[0070] In order to accurately understand the real-time status and surrounding environment of the vehicle, therefore, executing step S20 can ensure that the intelligent driving system can make correct decisions in a timely manner.

[0071] In a feasible implementation, step S20 may include step S21:

[0072] Step S21, based on a predefined state set and / or a vehicle operation state set, identifying the driving state of each frame in the intelligent driving data.

[0073] Optionally, first, the predefined state set includes {state initialization, state shutdown, state preparation stage, state activation, state position}. The predefined vehicle operation state set includes {driving, parking}.

[0074] Then, the intelligent driving data is sorted in chronological order, ensuring that the analysis starts from the earliest frame, i.e., the start frame. Then, each frame of intelligent driving data is analyzed to identify the driving state in the current frame. The driving state of the current frame is identified by parsing sensor data, such as vehicle speed, acceleration, steering angle, etc., as well as environmental perception data, such as surrounding vehicles, pedestrians, traffic signals, etc.

[0075] Next, the identified driving state is compared with the "state activation" in the state set and the "driving" in the vehicle operation state set to determine whether the driving state corresponding to the current frame is in the activation state and / or driving.

[0076] Once it is determined that a frame of data belongs to the "state activation" and / or "driving" state, the driving state corresponding to the activation state is further determined.

[0077] Examples are given for intelligent driving based on high-precision maps, intelligent driving based on perception maps, driving based on adaptive cruise control systems, and human driving. Figure 2 , Figure 2 This is a schematic diagram of the frame-level driving status determination process.

[0078] Optionally, if the intelligent driving state based on the high-precision map of the frame is activated, the driving state of this frame is the intelligent driving state based on the high-precision map. If the intelligent driving state based on the high-precision map corresponding to the frame is not activated, it is further determined whether the intelligent driving state based on the perception map is activated.

[0079] Similarly, if the intelligent driving state based on the perception map of the frame is activated, the driving state of this frame is the intelligent driving state based on the perception map. If the intelligent driving state based on the perception map of the frame is not activated, it is further determined whether the driving state based on the adaptive cruise system is activated.

[0080] Similarly, if the driving state based on the adaptive cruise system of the frame is an activated state, the driving state of this frame is a driving state based on the adaptive cruise system. If the driving state based on the adaptive cruise system of the frame is not an activated state, it is further determined whether the vehicle operation state is driving.

[0081] If the vehicle operation state of the frame is driving, the driving state of this frame is human driving state.

[0082] Through the above steps, by identifying whether the driving status in different frame data is in the "activated state" and thus determining the driving status corresponding to different frame data, it is ensured that the intelligent driving system is only activated under appropriate conditions, which can significantly improve driving safety and reliability. At the same time, it also provides data support for the subsequent work of distinguishing driving status.

[0083] Step S30, calculating the proportion of the driving state corresponding to the intelligent driving data according to the driving state of each frame in the intelligent driving data;

[0084] In order to better identify common driving conditions in specific driving scenarios, it is necessary to calculate the proportions of different driving conditions so as to optimize the intelligent driving algorithm in a targeted manner and improve the performance and safety of the intelligent driving system in similar scenarios.

[0085] In a feasible implementation, step S30 may include steps S31 to S33:

[0086] Step S31, counting the number of driving states in which the state flag bit of the corresponding driving state in the driving state scene-level list is marked with a first tag;

[0087] Optionally, first, the continuous intelligent data stream is segmented into multiple frame data segments according to the timestamp, and valid frame data segments are identified, wherein the valid frame data segments refer to data segments that contain key driving information and are of great value for analyzing vehicle behavior, environmental response, and system performance during the intelligent driving process.

[0088] Then, a valid frame data segment in each driving state scene-level list is identified, and a corresponding valid driving state is identified on the valid frame data segment.

[0089] Next, the driving state pre-tagged with the first label is searched on the state flag bit corresponding to the valid driving state, and the total number of times the driving state pre-tagged with the first label appears in the limited frame data segment is counted.

[0090] Step S33: Calculate the proportion of the corresponding driving states based on the number of corresponding driving states in the finite frame data segment marked with the first label.

[0091] In order to evaluate the relative frequency of a specific driving state (ie, the state represented by the first tag) in the entire valid frame data segment, step S33 is performed to help the driver understand the driving state of the vehicle in a specific scenario.

[0092] In a feasible implementation, step S33 may include steps A1-A2:

[0093] Step A1, calculating the number of elements from the start frame to the end frame;

[0094] It should be noted that the valid frame data segment includes a start frame and an end frame, and the start frame is recorded as frame_start and the end frame is recorded as frame_end.

[0095] Optionally, frame_start is used as the start index of the pre-created scene-level list, and frame_end is used as the end index to obtain the number of elements between frame_start and frame_end, wherein the number of elements is obtained by frame_end-frame_start.

[0096] Step A2: Divide the number of driving states marked with the first label by the number of elements between the start frame and the end frame to obtain the proportion of the corresponding driving states.

[0097] Optionally, the number of elements whose corresponding driving status flag is the first label in the valid frame data segments in the pre-created scene-level list is counted.

[0098] After obtaining the number of elements with the first label in the status flag corresponding to the valid driving state in the valid frame data segment, divide the number of elements with the first label in the valid driving state flag corresponding to the valid frame data segment by the number of elements between frame_start and frame_end (the number of elements between the start frame and the end frame) to obtain the corresponding proportions of different driving states.

[0099] Take the intelligent driving state based on high-precision maps (NZP), the intelligent driving state based on perception maps (LCC), the driving state based on adaptive cruise system (ACC) and the human driving state as examples.

[0100] With frame_start as the list start index and frame_end as the end index, extract the NZP state in the valid data segment from the pre-created scene-level list (state_NZP_scene_list) corresponding to the NZP state, such as Figure 3 As shown, Figure 3 This is a schematic diagram of the NZP state of the valid data segment extracted from state_NZP_scene_list. Then, calculate the number of elements in the valid data segment whose NZP state flag is the first label (nzp_sum), and then divide nzp_sum by the number of elements between the end frame and the start frame (frame_end-frame_start) to get the corresponding ratio of the NZP state (NZP_state_ratio).

[0101] Similarly, with frame_start as the start index of the list and frame_end as the end index, extract the LCC state in the valid data segment from the scene-level list (state_LCC_scene_list) corresponding to the pre-created LCC state, calculate the number of elements with the LCC state flag as the first label in the valid data segment (lcc_sum), and divide lcc_sum by the number of elements between the end frame and the start frame (frame_end-frame_start) to obtain the corresponding proportion of the LCC state (LCC_state_ratio).

[0102] Similarly, with frame_start as the start index of the list and frame_end as the end index, extract the ACC state in the valid data segment from the pre-created scene-level list corresponding to the ACC state (state_ACC_scene_list), calculate the number of elements with the ACC state flag as the first label in the valid data segment (acc_sum), and divide acc_sum by the number of elements between the end frame and the start frame (frame_end-frame_start) to get the corresponding proportion of the ACC state (ACC_state_ratio).

[0103] Similarly, with frame_start as the start index of the list and frame_end as the end index, extract the human driving state in the valid data segment from the pre-created scene-level list corresponding to the human driving state (state_human_scene_list), calculate the number of elements with the human driving state flag as the first label in the valid data segment (human_sum), and divide human_sum by the number of elements between the end frame and the start frame (frame_end-frame_start) to obtain the corresponding proportion of the human driving state (human_state_ratio).

[0104] Through the above steps, by extracting, counting and calculating the frequency of occurrence of specific driving states, the behavioral characteristics of the vehicle in different driving scenarios can be obtained, and then the intelligent driving algorithm can be optimized to improve driving safety and efficiency.

[0105] Step S40, determining the driving state of the current scene according to the proportion of the driving state, and obtaining corresponding driving data based on the driving state of the current scene

[0106] After the proportion of the driving state in each frame is determined in step S30, the driving state of the current scene and the corresponding driving data need to be determined according to the proportion of the driving state in each frame.

[0107] In a feasible implementation, step S40 may include steps S41 to S44:

[0108] Step S41, comparing the proportions of different driving states to obtain the driving state corresponding to the maximum proportion value;

[0109] Optionally, from the proportions corresponding to different driving states obtained in step S30, all different driving states and their percentages are listed. The proportions of each driving state are compared one by one to find the driving state with the highest proportion. The driving state with the largest proportion is marked as the dominant driving state in the current scene.

[0110] Step S42, comparing the driving state corresponding to the maximum proportion value with a preset threshold;

[0111] In order to verify whether the proportion of the dominant driving state is significant enough to ensure that it truly represents the main behavior of the current scene, in this embodiment, a threshold is pre-set, which is used to determine whether the proportion of the dominant driving state is large enough to be identified as a typical state of the current scene.

[0112] Optionally, a threshold is set based on experience or specific needs, and this threshold should be able to reflect the extent to which a driving state can be considered to dominate the current scene. The maximum proportion value determined in step S41 is compared with a preset threshold. If the maximum proportion value exceeds the preset threshold, the significance of the driving state is confirmed, otherwise, further analysis or consideration of other states may be required.

[0113] Step S43: if the driving state corresponding to the maximum proportion value is greater than the preset threshold value, determining the driving state corresponding to the maximum proportion value as the driving state of the current scene;

[0114] Based on the analysis of the first two steps, it is confirmed whether the driving state corresponding to the maximum proportion value can be officially recognized as the driving state of the current scene. If the conditions are met, the driving state corresponding to the maximum proportion value is the driving state of the current scene.

[0115] For example, take the driving state corresponding to the largest value among the proportion of the intelligent driving state (NZP) based on the high-precision map (NZP_state_ratio), the proportion of the intelligent driving state (LCC) based on the perception map (LCC_state_ratio), the proportion of the driving state based on the adaptive cruise system (ACC) (ACC_state_ratio), and the proportion of the human driving state (human_state_ratio). Set a threshold. When the maximum value is greater than this threshold, it means that the confidence of the driving state of the task is high, and this is used as the driving state of the scene.

[0116] Step S44, obtaining corresponding driving data based on the driving status of the current scene.

[0117] Once the driving state of the current scene is determined, the driving data related to the driving state is further filtered and marked.

[0118] Driving data of the current scenario can be used to train and verify the intelligent driving system, especially when simulating and reproducing similar scenarios, which helps to improve the system's processing capabilities and safety under specific driving conditions.

[0119] Through the above steps, the intelligent driving system can extract meaningful information from a large amount of intelligent driving data and identify the main driving status of the vehicle in the current scenario. It not only helps to adjust the driving strategy in real time and improve driving safety and efficiency, but also provides useful empirical data for future system optimization. Through the main driving status of the vehicle in the current scenario, the corresponding driving data can be further obtained, which effectively promotes the optimization of the intelligent driving data set.

[0120] Through the above-mentioned embodiment method, by acquiring intelligent driving data; identifying the driving status of different frames in the intelligent driving data; extracting the proportion of driving status of different frames according to the valid frame data fragments in the intelligent driving data; and determining the driving status of the current scene according to the proportion of driving status. This solution determines the driving status of the current vehicle driving scene by the proportion of different driving statuses, which can improve the overall performance of the intelligent driving system, and can also be optimized for specific application scenarios. By distinguishing the driving data corresponding to different driving statuses, it effectively promotes the optimization of the intelligent driving data set, thereby achieving more efficient and accurate training and iteration of the intelligent driving algorithm.

[0121] Based on the first embodiment of the present application, in the second embodiment of the present application, the same or similar contents as those in the above-mentioned embodiment 1 can be referred to the above introduction, and will not be repeated in the following. Figure 4 After step S20, the data processing method further includes steps S201 to S204:

[0122] Step S201, creating a corresponding driving state scene level list according to the driving state of each frame in the intelligent driving data, wherein the driving state scene level list is used to record the corresponding driving state;

[0123] It should be noted that in the field of intelligent driving and autonomous driving, the driving status field list refers to a structured data set used to record and organize the driving status and related information of the vehicle in a specific scenario. This list is usually a time series, which means that it stores the driving status data of the vehicle at different time points in chronological order, and each time point or frame corresponds to the real-time status of the vehicle.

[0124] Step S202, determining whether the driving state corresponding to the driving state scene-level list is consistent with the preset driving state;

[0125] Confirm again whether the driving state corresponding to the element recorded in each frame of data in the scene list is the same as the preset driving state.

[0126] Step 203: If yes, mark the first tag on the state flag corresponding to the driving state in the driving state scene level list;

[0127] Optionally, when the driving state corresponding to the element recorded in each frame of valid data in the driving state scene-level list is consistent with the preset driving state, a first label is marked on the corresponding state flag of the driving state in the driving state scene-level list, wherein, in this embodiment, the first label can be represented by "1", that is, "1" is filled in the corresponding state flag.

[0128] In addition, when the driving status corresponding to the element recorded on each frame data in the scene list is inconsistent with the preset driving status, a second label is marked at the corresponding position of the frame data in the scene level list. In this embodiment, the second label can be represented by "0", that is, "0" is filled in the corresponding frame index position.

[0129] For example, define a scene-level list (state_NZP_scene_list) corresponding to the intelligent driving state (NZP) based on a high-precision map. This scene list is used to store intelligent driving state information based on a high-precision map. Determine whether each frame in state_NZP_scene_list is in the NZP state, where each element represents the NZP state of the frame. If it is in the NZP state, fill 1 in the corresponding frame index position, otherwise, fill 0 in the corresponding frame index position.

[0130] Similarly, define the scene-level list (state_LCC_scene_list) corresponding to the intelligent driving state (LCC) based on the perception map. This scene list is used to store the intelligent driving state information based on the perception map. Determine whether each frame in the state_LCC_scene_list is in the LCC state, where each element represents the LCC state of the frame. If it is the LCC state, fill 1 in the corresponding frame index position, otherwise, fill 0 in the corresponding frame index position.

[0131] Similarly, define the scene-level list (state_ACC_scene_list) corresponding to the driving state (ACC) based on the adaptive cruise system. This scene list is used to store the driving state information based on the adaptive cruise system. Determine whether each frame in state_LCC_scene_list is in the ACC state, where each element represents the ACC state of the frame. If it is in the ACC state, fill 1 in the corresponding frame index position, otherwise fill 0 in the corresponding frame index position.

[0132] Similarly, define the scene-level list corresponding to the human driving state (state_human_scene_list), which is used to store the human driving state information. Determine whether each frame in state_LCC_human_list is in the human driving state, where each element represents the human driving state of the frame. If it is a human driving state, fill 1 in the corresponding frame index position, otherwise, fill 0 in the corresponding frame index position.

[0133] Through the above-mentioned embodiment method, by defining the corresponding scene-level list and storing each frame of driving status information in chronological order, subsequent data analysis and backtracking are facilitated; by using binary tags (1 or 0), it is possible to quickly identify which frame data is data under the preset driving state and which is not, which not only realizes the effective management and analysis of driving status information, but also promotes the continuous optimization of the intelligent driving system and the improvement of safety performance, while providing users with a safer, more comfortable and reliable driving experience.

[0134] It should be noted that the above examples are only used to understand the present application and do not constitute a limitation on the data processing method of the present application. More simple transformations based on this technical concept are all within the scope of protection of the present application.

[0135] This application also provides a data processing device, please refer to Figure 5 , the data processing device comprises:

[0136] An acquisition module 10 is used to acquire intelligent driving data;

[0137] An identification module 20, used to identify the driving state of each frame in the intelligent driving data;

[0138] A calculation module 30, configured to calculate a proportion of the driving state corresponding to the intelligent driving data according to the driving state of each frame in the intelligent driving data;

[0139] The determination module 40 is used to determine the driving state of the current scene according to the proportion of the driving state, and obtain corresponding driving data based on the driving state of the current scene.

[0140] The data processing device provided by the present application adopts the data processing method in the above embodiment, which can solve the technical problem of how to distinguish the driving data corresponding to the driving state of the intelligent driving data set. Compared with the prior art, the beneficial effects of the data processing device provided by the present application are the same as the beneficial effects of the data processing method provided by the above embodiment, and the other technical features in the data processing device are the same as the features disclosed in the above embodiment method, which will not be repeated here.

[0141] The present application provides a data processing device, which includes: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute the data processing method in the above-mentioned embodiment 1.

[0142] Reference below Figure 6 , which shows a schematic diagram of the structure of a data processing device suitable for implementing an embodiment of the present application. The data processing device in the embodiment of the present application may include, but is not limited to, mobile terminals such as mobile phones, laptop computers, digital broadcast receivers, PDAs (Personal Digital Assistants), PADs (Portable Application Descriptions), PMPs (Portable Media Players), vehicle-mounted terminals (such as vehicle-mounted navigation terminals), etc., and fixed terminals such as digital TVs, desktop computers, etc. Figure 6 The data processing device shown is only an example and should not bring any limitation to the functions and scope of use of the embodiments of the present application.

[0143] like Figure 6As shown, the data processing device may include a processing device 1001 (such as a central processing unit, a graphics processor, etc.), which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM: Read Only Memory) 1002 or a program loaded from a storage device 1003 to a random access memory (RAM: Random Access Memory) 1004. In RAM1004, various programs and data required for the operation of the data processing device are also stored. The processing device 1001, ROM1002 and RAM1004 are connected to each other through a bus 1005. An input / output (I / O) interface 1006 is also connected to the bus. Generally, the following systems can be connected to the I / O interface 1006: an input device 1007 including, for example, a touch screen, a touch pad, a keyboard, a mouse, an image sensor, a microphone, an accelerometer, a gyroscope, etc.; an output device 1008 including, for example, a liquid crystal display (LCD: Liquid Crystal Display), a speaker, a vibrator, etc.; a storage device 1003 including, for example, a magnetic tape, a hard disk, etc.; and a communication device 1009. The communication device 1009 can allow the data processing device to communicate with other devices wirelessly or by wire to exchange data. Although the figure shows a data processing device with various systems, it should be understood that it is not required to implement or have all the systems shown. More or fewer systems can be implemented or have alternatively.

[0144] In particular, according to the embodiments disclosed in the present application, the process described above with reference to the flowchart can be implemented as a computer software program. For example, the embodiments disclosed in the present application include a computer program product, which includes a computer program carried on a computer-readable medium, and the computer program includes a program code for executing the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from a network through a communication device, or installed from a storage device 1003, or installed from a ROM 1002. When the computer program is executed by the processing device 1001, the above-mentioned functions defined in the method of the embodiment disclosed in the present application are executed.

[0145] The data processing device provided by the present application adopts the data processing method in the above embodiment, which can solve the technical problem of how to distinguish the driving data corresponding to the driving state of the intelligent driving data set. Compared with the prior art, the beneficial effects of the data processing device provided by the present application are the same as the beneficial effects of the data processing method provided by the above embodiment, and the other technical features in the data processing device are the same as the features disclosed in the method of the previous embodiment, which will not be repeated here.

[0146] It should be understood that the various parts disclosed in this application can be implemented by hardware, software, firmware or a combination thereof. In the description of the above embodiments, specific features, structures, materials or characteristics can be combined in any one or more embodiments or examples in a suitable manner.

[0147] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art who is familiar with the present technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.

[0148] The present application provides a computer-readable storage medium having computer-readable program instructions (ie, computer programs) stored thereon, wherein the computer-readable program instructions are used to execute the data processing method in the above-mentioned embodiment.

[0149] The computer-readable storage medium provided in the present application may be, for example, a USB flash drive, but is not limited to electrical, magnetic, optical, electromagnetic, infrared, or semiconductor systems, systems or devices, or any combination of the above. More specific examples of computer-readable storage media may include, but are not limited to: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM: Random Access Memory), a read-only memory (ROM: Read Only Memory), an erasable programmable read-only memory (EPROM: Erasable Programmable Read Only Memory or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM: CD-Read Only Memory), an optical storage device, a magnetic storage device, or any suitable combination of the above. In this embodiment, the computer-readable storage medium may be any tangible medium containing or storing a program, which may be used by or in combination with an instruction execution system, system or device. The program code contained on the computer-readable storage medium may be transmitted using any appropriate medium, including but not limited to: wires, optical cables, RF (Radio Frequency: Radio Frequency), etc., or any suitable combination of the above.

[0150] The computer-readable storage medium may be included in a data processing device, or may exist independently without being incorporated into a data processing device.

[0151] The above-mentioned computer-readable storage medium carries one or more programs. When the above-mentioned one or more programs are executed by a data processing device, the data processing device is enabled to: obtain intelligent driving data; identify the driving status of different frames in the intelligent driving data; extract the proportion of the driving status of the different frames based on the valid frame data fragments in the intelligent driving data; and determine the driving status of the current scene based on the proportion of the driving status.

[0152] Computer program code for performing the operations of the present application may be written in one or more programming languages ​​or a combination thereof, including object-oriented programming languages ​​such as Java, Smalltalk, C++, and conventional procedural programming languages ​​such as "C" or similar programming languages. The program code may be executed entirely on the user's computer, partially on the user's computer, as a separate software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0153] The flow chart and block diagram in the accompanying drawings illustrate the possible architecture, function and operation of the system, method and computer program product according to various embodiments of the present application. In this regard, each square box in the flow chart or block diagram can represent a module, a program segment or a part of a code, and the module, the program segment or a part of the code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the square box can also occur in a sequence different from that marked in the accompanying drawings. For example, two square boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each square box in the block diagram and / or flow chart, and the combination of the square boxes in the block diagram and / or flow chart can be implemented with a dedicated hardware-based system that performs a specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.

[0154] The modules involved in the embodiments described in this application may be implemented by software or hardware, wherein the name of the module does not constitute a limitation on the unit itself in some cases.

[0155] The readable storage medium provided in the present application is a computer-readable storage medium, which stores computer-readable program instructions (i.e., computer programs) for executing the above-mentioned data processing method, and can solve the technical problem of how to distinguish the driving data corresponding to the driving state of the intelligent driving data set. Compared with the prior art, the beneficial effects of the computer-readable storage medium provided in the present application are the same as the beneficial effects of the data processing method provided in the above-mentioned embodiment, and will not be repeated here.

[0156] The present application also provides a computer program product, including a computer program, which implements the steps of the above-mentioned data processing method when executed by a processor.

[0157] The computer program product provided by the present application can solve the technical problem of how to distinguish the driving data corresponding to the driving status of the intelligent driving data set. Compared with the prior art, the beneficial effects of the computer program product provided by the present application are the same as the beneficial effects of the data processing method provided by the above embodiment, which will not be repeated here.

[0158] The above descriptions are only some embodiments of the present application, and are not intended to limit the patent scope of the present application. All equivalent structural changes made using the contents of the present application specification and drawings under the technical concept of the present application, or direct / indirect applications in other related technical fields are included in the patent protection scope of the present application.

Claims

1. A data processing method, characterized in that: The method comprises: Obtain intelligent driving data; Identifying the driving state of each frame in the intelligent driving data, including: comparing the driving state with the state activation in the state set and the driving in the vehicle operation state set, judging whether the driving state corresponding to the current frame is in the activation state and / or driving, so as to determine the driving state corresponding to the activation state, wherein the driving state includes at least the NZP state, the LCC state, the ACC state and the human driving state; According to the driving state of each frame in the intelligent driving data, calculating the proportion of the driving state corresponding to the intelligent driving data; According to the proportion of the driving status, the driving status of the current scene is determined, and corresponding driving data is obtained based on the driving status of the current scene, including: comparing the proportions of different driving statuses to obtain the driving status corresponding to the maximum proportion value; comparing the driving status corresponding to the maximum proportion value with a preset threshold value; if the driving status corresponding to the maximum proportion value is greater than the preset threshold value, determining the driving status corresponding to the maximum proportion value as the driving status of the current scene; and obtaining corresponding driving data based on the driving status of the current scene.

2. The method according to claim 1, characterized in that The step of identifying the driving state of each frame in the intelligent driving data comprises: Based on a predefined state set and / or a vehicle operation state set, the driving state of each frame in the intelligent driving data is identified.

3. The method according to claim 2, characterized in that The driving state includes an intelligent driving state NZP state based on a high-precision map, an intelligent driving state LCC based on a perception map, an ACC state based on an adaptive cruise system, and a human driving state. The predefined state set includes state activation, and the predefined vehicle operation state set includes driving. The step of identifying the driving state of each frame in the intelligent driving data based on the predefined state set and / or the vehicle operation state set includes: Determine whether the NZP state of each frame in the intelligent driving data is state activated; If the NZP state of each frame in the intelligent driving data is state activated, determining that the driving state corresponding to each frame in the intelligent driving data is the NZP state; If the NZP state of each frame in the intelligent driving data is not state activated, determining whether the LCC state of each frame in the intelligent driving data is LCC state activated; If the LCC state of each frame in the intelligent driving data is state activated, determining that the driving state corresponding to each frame in the intelligent driving data is the LCC state; If the LCC state of each frame in the intelligent driving data is not state activated, determining whether the ACC state of each frame in the intelligent driving data is state activated; If the ACC state of each frame in the intelligent driving data is state activated, determining that the driving state corresponding to each frame in the intelligent driving data is the ACC state; If the ACC state of each frame in the intelligent driving data is not the activated state, determining whether the human driving state of each frame in the intelligent driving data is driving; If the human driving state of each frame in the intelligent driving data is driving, it is determined that the driving state corresponding to each frame in the intelligent driving data is the human driving state.

4. The method according to claim 2, characterized in that After the step of identifying the driving state of each frame in the intelligent driving data, the method further includes: According to the driving state of each frame in the intelligent driving data, a corresponding driving state scene level list is created, wherein the driving state scene level list is used to record the corresponding driving state; Determine whether the driving state corresponding to the driving state scene-level list is consistent with the preset driving state; If yes, marking a first label on the state flag corresponding to the driving state in the driving state scene level list; According to the driving state of each frame in the intelligent driving data, the step of calculating the proportion of the driving state corresponding to the intelligent driving data comprises: Counting the number of driving states in which the state flag bit of the corresponding driving state in the driving state scene-level list is marked with the first label; Based on the number of corresponding driving states in the finite frame data segment marked with the first label, the proportion of the corresponding driving states is calculated.

5. The method according to claim 4, characterized in that The step of calculating the proportion of the corresponding driving states based on the number of driving states marked with the first tag includes: Calculate the number of elements from the start frame to the end frame; The number of driving states marked with the first label is divided by the number of elements between the start frame and the end frame to obtain the proportion of the corresponding driving state.

6. A data processing device, characterized in that: The device comprises: An acquisition module, used to acquire intelligent driving data; an identification module, for identifying the driving state of each frame in the intelligent driving data, including: comparing the driving state with the state activation in the state set and the driving in the vehicle operation state set, judging whether the driving state corresponding to the current frame is in the activation state and / or driving, so as to determine the driving state corresponding to the activation state, wherein the driving state includes at least the NZP state, the LCC state, the ACC state and the human driving state; A calculation module, used to calculate the proportion of the driving state corresponding to the intelligent driving data according to the driving state of each frame in the intelligent driving data; A determination module is used to determine the driving state of the current scene according to the proportion of the driving state, and obtain corresponding driving data based on the driving state of the current scene, including: comparing the proportions of different driving states to obtain the driving state corresponding to the maximum proportion value; comparing the driving state corresponding to the maximum proportion value with a preset threshold; if the driving state corresponding to the maximum proportion value is greater than the preset threshold, determining that the driving state corresponding to the maximum proportion value is the driving state of the current scene; and obtaining corresponding driving data based on the driving state of the current scene.

7. A data processing device, characterized in that: The device comprises: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the computer program is configured to implement the steps of the data processing method according to any one of claims 1 to 5.

8. A storage medium, characterized in that: The storage medium is a computer-readable storage medium, and a computer program is stored on the storage medium. When the computer program is executed by a processor, the steps of the data processing method according to any one of claims 1 to 5 are implemented.

9. A computer program product, characterized in that The computer program product comprises a computer program, and when the computer program is executed by a processor, the steps of the data processing method according to any one of claims 1 to 5 are implemented.

Images