An emulation data generation method, apparatus, device, and medium

Abstract

The application discloses a kind of simulation data generation method, device, equipment and medium.The method comprises: obtaining test scene generation condition, finds target vehicle data information and roadside data information satisfying test scene generation condition based on the data label set of pre-constructed database;Target vehicle data information and roadside data information are processed in time length format, and data group package is obtained;Determine the data point set to be supplemented of data group package, and the data point set to be supplemented is processed in directed graph track, and fence map information is obtained;According to fence map information, the data point set to be supplemented is supplemented, and the final test data package is obtained.The pre-constructed database constructed by real vehicle data is matched with the data of test scene generation condition according to the data label set through different dimensions, and then data grouping and point supplementing are carried out to obtain the final test data package.The authenticity and availability of the final test data are guaranteed, and the adaptability of the data is improved.

Description

Technical Field

[0001] This invention relates to the field of intelligent transportation technology, and in particular to a method, apparatus, equipment and medium for generating simulation data. Background Technology

[0002] Vehicle-road cooperation is the current development direction for the practical application of Internet of Vehicles technology. The core hardware of the vehicle-road cooperation system consists of the on-board unit (OBU) installed on the vehicle and the roadside unit (RSU) deployed on the roadside. As an emerging industry, vehicle-road cooperation still has some problems to overcome, such as the stability of application algorithms and the rationality of application triggering effects.

[0003] Currently, to address issues such as the effectiveness of application algorithms and the rationality of triggering effects, directly using real-vehicle road tests is not only time-consuming and costly, but also poses significant safety risks by testing applications on the road without prior verification. Therefore, simulation testing methods are needed for verification.

[0004] The biggest problem with using simulation testing for verification is that the generation of simulation test cases is random, resulting in some long-tail scenarios not being covered or generated, and the generated scenarios being detached from the actual scenarios, leading to low realism of the test cases. Most of the generated scenarios are unusable, and it wastes resources and verification time. Summary of the Invention

[0005] This invention provides a method, apparatus, device, and medium for generating simulation data, so as to achieve the generation of high-quality simulation data.

[0006] According to a first aspect of the present invention, a method for generating simulation data is provided, comprising:

[0007] Obtain the test scenario generation conditions, and search for target vehicle data information and roadside data information that meet the test scenario generation conditions based on the data tag set of the pre-built database;

[0008] The target vehicle data information and the roadside data information are processed in a time-length format to obtain a data packet;

[0009] The set of data points to be supplemented in the data package is determined, and the set of data points to be supplemented is subjected to directed graph trajectory processing to obtain fence map information.

[0010] The data point set to be supplemented is supplemented based on the fence map information to obtain the final test data package.

[0011] According to a second aspect of the present invention, a simulation data generation apparatus is provided, comprising:

[0012] The information acquisition module is used to acquire the test scenario generation conditions and search for target vehicle data information and roadside data information that meet the test scenario generation conditions based on the data tag set of the pre-built database.

[0013] The data packetization module is used to process the target vehicle data information and the roadside data information in terms of time and format to obtain data packets;

[0014] The information determination module is used to determine the set of data points to be supplemented in the data package, and to perform directed graph trajectory processing on the set of data points to be supplemented to obtain fence map information.

[0015] The test case generation module is used to supplement the data point set to be supplemented based on the fence map information to obtain the final test data package.

[0016] According to a third aspect of the present invention, an electronic device is provided, the electronic device comprising:

[0017] At least one processor; and

[0018] A memory communicatively connected to the at least one processor; wherein,

[0019] The memory stores a computer program that can be executed by the at least one processor, which enables the at least one processor to perform the simulation data generation method according to any embodiment of the present invention.

[0020] According to a fourth aspect of the present invention, a computer-readable storage medium is provided, the computer-readable storage medium storing computer instructions for causing a processor to execute and implement the simulation data generation method according to any embodiment of the present invention.

[0021] The technical solution of this invention involves obtaining test scenario generation conditions, searching for target vehicle data and roadside data that meet these conditions based on a pre-built database's data tag set, processing the target vehicle data and roadside data for duration format to obtain data packets, determining the data point set to be supplemented within the data packets, and performing directed graph trajectory processing on this data point set to obtain fence map information, and supplementing the data point set according to the fence map information to obtain the final test data packet. By using a pre-built database constructed from real vehicle data, data matching the test scenario generation conditions is determined according to different dimensions based on the data tag set, and then data packets are assembled and supplemented to obtain the final test data packet. This ensures the authenticity and usability of the final test data and improves data adaptability.

[0022] It should be understood that the description in this section is not intended to identify key or essential features of the embodiments of the present invention, nor is it intended to limit the scope of the invention. Other features of the invention will become readily apparent from the following description. Attached Figure Description

[0023] To more clearly illustrate the technical solutions in the embodiments of the present invention, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0024] Figure 1 This is a flowchart of a simulation data generation method provided in Embodiment 1 of the present invention;

[0025] Figure 2 This is a flowchart of a simulation data generation method provided in Embodiment 2 of the present invention;

[0026] Figure 3 This is an example diagram of a fence map in a simulation data generation method provided according to Embodiment 2 of the present invention;

[0027] Figure 4 This is a schematic diagram of the structure of a simulation data generation device according to Embodiment 3 of the present invention;

[0028] Figure 5 This is a schematic diagram of the structure of an electronic device that implements an embodiment of the present invention. Detailed Implementation

[0029] To enable those skilled in the art to better understand the present invention, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings of the embodiments of the present invention. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort should fall within the scope of protection of the present invention.

[0030] It should be noted that the terms "first," "second," etc., in the specification, claims, and accompanying drawings of this invention are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of the invention described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover a non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0031] Example 1

[0032] Figure 1 This is a flowchart of a simulation data generation method provided in Embodiment 1 of the present invention. This embodiment is applicable to the generation of simulation data under different scenario conditions. The method can be executed by a simulation data generation device, which can be implemented in hardware and / or software and can be configured in an electronic device. Figure 1 As shown, the method includes:

[0033] S110. Obtain the test scenario generation conditions, and search for target vehicle data information and roadside data information that meet the test scenario generation conditions based on the data tag set of the pre-built database.

[0034] In this embodiment, the test scenario generation conditions can be understood as the requirements for generating test cases, such as parameters like the scenario trigger range, the number of vehicles in the environment, the scenario time, and weather requirements. The pre-built database can be understood as a database based on real vehicle information and roadside information under different scenarios. The data tag set can be understood as a set of tags used to distinguish the type of data, such as area tags, event type tags, scenario tags, and road type tags, with different classifications under each tag. The target vehicle data information can be understood as the real vehicle data that best matches the test scenario generation conditions, such as the time, scenario category, road conditions, and weather data of the main vehicle and related slave vehicles that triggered the scenario conditions at historical moments. Roadside data information can be understood as messages sent by roadside devices within a certain distance range of the location involved in the target vehicle data information, such as information about accidents ahead.

[0035] It is understandable that test scenario generation conditions can be formed in two forms. One is to add target vehicle data and roadside data information generated when the scenario is triggered to the pre-built database. The other is to provide parameters and data requirements to the users of the pre-built database. Optional conditions can be displayed to the users by setting options. For example, the weather requirements can include: sunny, rainy, backlight, fog, and snow. Using this as an example, by using the user's selection according to the corresponding tag number, the processor can automatically generate the corresponding test scenario generation conditions, or directly generate test scenario generation conditions based on the text entered by the user.

[0036] Specifically, when the processor receives test scenario generation conditions from the pre-built database or the user of the pre-built database, it compares the test scenario generation conditions with the data tag set of the built database in sequence to find the target vehicle data information that meets the test scenario generation conditions, as well as the roadside data information of the roadside equipment at the location of the target vehicle data information.

[0037] For example, the test scenario generation conditions are: backlight, intersection, three-vehicle collision, and 3 PM. The test scenario generation conditions can be used to search the pre-built database using a data tag set to determine the target vehicle data information tagged with "backlight," "intersection," "three-vehicle collision," and "3 PM," as well as the roadside data information of the roadside equipment located at the target vehicle's location.

[0038] S120. Process the target vehicle data and roadside data in a time-length format to obtain a data package.

[0039] In this embodiment, a data packet can be understood as a data packet that combines target vehicle data information and roadside data information.

[0040] Specifically, since the required restoration time varies in different scenarios, and the target vehicle data includes information about a long period of time before and after the scenario is triggered, directly using this information may result in a long period of useless time. For example, in a rear-end collision scenario, it may be necessary to determine how the rear-end collision occurred, such as the following vehicle changing lanes or the preceding vehicle cutting in front, causing the main vehicle to be rear-ended. The target vehicle data and roadside data can be pre-set with the corresponding duration for different scenarios, and aligned according to time to ensure that the time points of the main vehicle, following vehicles, and environmental data are consistent. Then, the pre-set and aligned data are assembled using a set format method to generate a unique scenario ID and obtain a data package.

[0041] S130. Determine the set of data points to be supplemented in the data package, and perform directed graph trajectory processing on the set of data points to be supplemented to obtain fence map information.

[0042] It's important to understand that the set of data points to be supplemented can be understood as the collection of points lacking data. Since different vehicles or business entities report data at inconsistent frequencies, supplementary data points are needed to ensure data availability at every time point in the simulation. Fence map information can be understood as a map representation using a grid system, with each grid assigned specific attribute information.

[0043] Specifically, since the main vehicle is used as the timeline for playback during scene simulation, the main vehicle is generally used as the time reference for supplementing data points. The set of data points to be supplemented corresponding to the data of other vehicles is determined from the time points corresponding to the main vehicle data in the data package. For example, the main vehicle includes time points A, B, C and D, while the vehicles only include time points A and C. Then B and D are the data points to be supplemented, which constitute the set of data points to be supplemented. The processor can draw a fence map based on the positional relationship between the data points to be supplemented belonging to the same vehicle in the set of data points to be supplemented. The processor can divide the fence map into a set number of squares with the same area, assign position information to each square, and obtain the fence map information.

[0044] S140. Supplement the data point set to be supplemented based on the fence map information to obtain the final test data package.

[0045] In this embodiment, the final test data packet can be understood as the processed data packet that meets the conditions for generating the test scenario.

[0046] Specifically, the processor can determine the predicted trajectory by performing directed graph trajectory analysis based on the vehicle data associated with the data point set to be supplemented in the fence map information. By determining the proportion of each square occupied by the predicted trajectory, the processor can determine which square the actual trajectory is in, and then assign time information to that square to complete the data point supplementation and obtain the final test data packet.

[0047] The technical solution of this invention involves obtaining test scenario generation conditions, searching for target vehicle data and roadside data that meet these conditions based on a pre-built database's data tag set, processing the target vehicle data and roadside data for duration format to obtain data packets, determining the data point set to be supplemented within the data packets, and performing directed graph trajectory processing on this data point set to obtain fence map information, and supplementing the data point set according to the fence map information to obtain the final test data packet. By using a pre-built database constructed from real vehicle data, data matching the test scenario generation conditions is determined according to different dimensions based on the data tag set, and then data packets are assembled and supplemented to obtain the final test data packet. This ensures the authenticity and usability of the final test data and improves data adaptability.

[0048] As a first optional embodiment of this embodiment, the steps for constructing the pre-built database include:

[0049] a1. Obtain the roadside location information of the associated roadside equipment.

[0050] In this embodiment, the associated roadside equipment can be understood as including roadside equipment that has an interaction protocol with the processor. Roadside location information can be understood as information about the location set by the roadside equipment and the message broadcasting range of the roadside equipment.

[0051] Specifically, the processor can receive roadside location information from associated roadside devices through a set interaction protocol.

[0052] b1. The roadside location information is mapped to point locations to obtain the roadside data map.

[0053] In this embodiment, the roadside data map can be understood as a visualization of the relationships between roadside data.

[0054] Specifically, the processor can map and point the roadside location information to obtain a roadside data map, so as to ensure that when a location-based scene is triggered, the information of roadside devices and related messages within the range can be quickly selected.

[0055] c1. Receive the original vehicle driving information of the target vehicle that triggered the scene collection conditions. The original vehicle driving information includes the first original information of the target vehicle and the second original information of the associated vehicle.

[0056] In this embodiment, scene acquisition conditions can be understood as the pre-set conditions corresponding to the scene for which data acquisition is required, such as scene acquisition conditions such as different types of collisions.

[0057] It is understood that the target vehicle can be understood as the vehicle that triggers the scene data collection conditions and has an interaction protocol configured with the processor. Since multiple vehicles may trigger the scene data collection conditions, one of them can be selected as the target vehicle, i.e., the master vehicle, which can receive vehicle data sent by other vehicles. The original vehicle driving information can be understood as including the driving information of the vehicle itself and other related vehicles. For example, driving information may include vehicle speed, heading angle, and map curvature. Since not all vehicles are configured with an interaction protocol, the driving information of related vehicles can be determined through roadside equipment or vehicles configured with an interaction protocol.

[0058] In this embodiment, the first raw information can be understood as the driving information of the target vehicle within a set time period before and after the triggering of the scenario collection conditions. Associated vehicles can be understood as vehicles that trigger the scenario collection conditions together with the target vehicle. For example, in a rear-end collision, if the rear-ending vehicle is the target vehicle, the rear-ended vehicle is the associated vehicle, and vice versa. The second raw information can be understood as the driving information of the associated vehicles within a set time period before and after the triggering of the scenario collection conditions.

[0059] Specifically, the processor can receive raw vehicle driving information sent by the target vehicle that triggers the scene acquisition conditions through a set interaction protocol. The raw vehicle driving information includes the first raw information of the target vehicle and the second raw information of the associated vehicle.

[0060] d1. Replace the identity information in the original vehicle driving information with a preset list of pointing values ​​to obtain the target vehicle driving information.

[0061] In this embodiment, the identification information can be understood as information used to identify the vehicle, such as license plate number and vehicle model. The preset pointer value list can be understood as a list used to represent identification through symbols or letters, for example, a car is represented by A, and a truck is represented by B. The target vehicle driving information can be understood as the replaced target vehicle driving information.

[0062] Specifically, to avoid leaking the identity of the target vehicle and related vehicles and to ensure privacy and security, the processor can identify the identity information used to represent the vehicle's identity in the original vehicle driving information, determine the corresponding pointer value in the preset pointer value list, and replace the identity information with the pointer value to obtain the target vehicle driving information.

[0063] e1. Tag the target vehicle's driving information to obtain vehicle data information containing tags.

[0064] In this embodiment, vehicle data information can be understood as target vehicle driving information containing tags.

[0065] Specifically, the processor can compare the information in the target vehicle's driving information that meets the tagging processing conditions with the preset tag value to determine the tag to which the target vehicle's driving information belongs, and obtain vehicle data information containing the tag.

[0066] f1. Establish a pre-built database based on the data tag set composed of each tag, vehicle data information and roadside data map.

[0067] Specifically, the processor can construct a data tag set based on tags of various types and tag values, and build a database by combining the corresponding vehicle data information and roadside data maps.

[0068] Furthermore, based on the above embodiments, the step of tagging the target vehicle's driving information to obtain vehicle data information containing tags can be optimized as follows:

[0069] Based on the scene collection conditions triggered by the target vehicle, determine the event type label; based on the preset business scope area, determine the business scope area to which the target vehicle is located, and the area label of the business scope area; based on the target vehicle's driving information, determine the road type label; obtain the environmental information of the target vehicle's location and determine the scene label; based on the event type label, area label, road type label, scene label, and target vehicle driving information, generate vehicle data information containing labels.

[0070] In this embodiment, the event type label can be understood as a label used to indicate the type of the triggered event. The preset service scope area can be understood as the pre-defined service area served by different services, for example, a service could be an area with location-based services (LBS). The service scope belonging area can be understood as the area where the vehicle is configured with preset service. The area label can be understood as a label used to indicate the service area where the vehicle is located. Environmental information can be understood as information such as weather conditions at the location. The road type label can be understood as a label used to indicate the type of road being traveled on, such as mountainous areas or cities. The scene label can be understood as information about the scene the vehicle is in, such as weather and the type of intersection (e.g., an intersection).

[0071] Specifically, the processor can automatically extract and label the target vehicle's driving information based on the scene acquisition conditions triggered by the target vehicle. The target vehicle simultaneously reports scene services, including key information such as time, scene category, scene name, and number of environmental devices. Since scene generation typically involves a corresponding service triggering area, the processor can determine the service area to which the first frame position of the target vehicle triggering the scene acquisition conditions belongs, along with the corresponding area label, based on a preset service area. The processor can also determine road conditions such as curves based on the curvature in the target vehicle's driving information, thus determining the road type label. Furthermore, the processor can obtain environmental information about the target vehicle's location using weather and map software, thereby determining the scene label. Finally, the processor can label the target vehicle's driving information with the corresponding tags based on the event type label, area label, road type label, and scene label, generating vehicle data information containing these tags.

[0072] The first optional embodiment of this example expands the sources of simulation data by collecting and summarizing real data of target vehicles that trigger scene acquisition conditions. Scenes generated from real vehicles are highly realistic, covering a wide range of long-tail scenarios. Furthermore, by automatically determining whether scene acquisition conditions are triggered, no driver intervention is required, achieving seamless data reporting. Automatic identification of vehicle identity data and replacement using a preset list of pointing values ​​yields the target vehicle's driving information, ensuring no data security or sensitivity issues arise during simulation and data usage. By tagging the target vehicle's driving information in different dimensions, vehicle data information containing tags is obtained. A pre-built database is constructed based on roadside data maps, vehicle data information, and data tag sets, improving data management and reducing the time spent selecting data during subsequent scene construction. The different dimensional tag divisions further enhance data adaptability.

[0073] Example 2

[0074] Figure 2 This is a flowchart of a simulation data generation method provided in Embodiment 2 of the present invention. This embodiment is a further refinement of the above embodiment. Figure 2 As shown, the method includes:

[0075] S201. Obtain the test scenario generation conditions and determine the main vehicle data information that matches the test scenario generation conditions based on the data tag set of the pre-built database.

[0076] In this embodiment, the main vehicle data information can be understood as the vehicle data information corresponding to the main vehicle set when constructing the database.

[0077] Specifically, the processor can obtain the test scenario generation conditions and compare them sequentially with the data label set of the constructed database according to the test scenario generation conditions. It can then find the main vehicle data information that matches the test scenario generation conditions from all the vehicle data information included in the pre-built database.

[0078] S202. Search the pre-built database for slave vehicle data information that is associated with the master vehicle data information.

[0079] In this embodiment, the slave vehicle data information can be understood as the vehicle data information of the slave vehicle associated with the master vehicle when the scenario is triggered.

[0080] Specifically, since the master vehicle and slave vehicle belonging to the same scene acquisition conditions are associated when the pre-built database is constructed, the processor can find slave vehicle data information associated with the master vehicle data information in the pre-built database.

[0081] S203. Use the master vehicle data information and slave vehicle data information as the target vehicle data information to meet the conditions for generating the test scenario.

[0082] Specifically, the processor can use the master vehicle data information and slave vehicle data information as target vehicle data information to meet the conditions for generating the test scenario.

[0083] S204. In the roadside data map of the pre-built database, determine the roadside data information corresponding to the location conditions in the test scenario generation conditions.

[0084] In this embodiment, the location condition can be understood as the set geographical location.

[0085] Specifically, the processor can search in the roadside data map of the pre-built database according to the location conditions generated in the test scenario. These location conditions can also be obtained from the target vehicle data information, thereby determining the roadside equipment at that location and acquiring the roadside data information.

[0086] S205. Based on the preset scene duration list, determine the target clipping duration that matches the target scene label in the target vehicle data information.

[0087] In this embodiment, the preset scene duration list can be understood as a list of pre-defined correspondences between scenes and durations. The target scene tag can be understood as a tag used to represent the scene being triggered. The target trimming duration can be understood as the trimming duration corresponding to the scene, such as X seconds before scene triggering + scene trigger time + X seconds after scene triggering.

[0088] Specifically, the processor can search for the target scene tag in the target vehicle data information in the preset scene duration list to determine the matching target clipping duration.

[0089] S206. Based on the target pruning time, the target vehicle data information is pruned to obtain intermediate vehicle data.

[0090] In this embodiment, intermediate vehicle data can be understood as vehicle data after time trimming, which also includes data of the master vehicle and slave vehicles.

[0091] Specifically, the processor can perform data pruning on the vehicle data of the master vehicle and slave vehicles in the target vehicle data information based on the target pruning time to obtain intermediate vehicle data.

[0092] S207. Align the intermediate master vehicle data and intermediate slave vehicle data in the intermediate vehicle data to obtain the final vehicle data.

[0093] In this embodiment, the intermediate master vehicle data information can be understood as the trimmed vehicle data information of the master vehicle. The intermediate slave vehicle data information can be understood as the trimmed vehicle data information of the slave vehicle.

[0094] Specifically, the processor can align the intermediate master vehicle data and intermediate slave vehicle data in the intermediate vehicle data according to the time point of each data point to obtain the final vehicle data, so as to ensure the consistency of the time points of the master vehicle, slave vehicle and environmental data.

[0095] S208. The final vehicle data and roadside data information are formatted based on the preset data format to obtain a data package.

[0096] In this embodiment, the preset data format can be understood as a structural format used for data assembly, such as a data frame, which is a tabular data structure.

[0097] Specifically, the processor can format the final vehicle data and roadside data information based on a preset data format (such as a dataframe) to obtain data packets and generate a unique scene ID.

[0098] S209. The data package includes the final master vehicle data information and the final slave vehicle data information. The first data time axis in the final master vehicle data information is compared with the second data time axis in the final slave vehicle data information to determine the set of data points to be supplemented in the slave vehicle data information.

[0099] In this embodiment, the master vehicle data information can be understood as the data information corresponding to the master vehicle in the data package. The first data timeline can be understood as the time corresponding to each data point in the master vehicle data information. The slave vehicle data information can be understood as the data information corresponding to the slave vehicle in the data package. The second data timeline can be understood as the time corresponding to each data point in the slave vehicle data information.

[0100] Specifically, the data package includes master vehicle data information and slave vehicle data information. The processor can compare the first data time axis in the final master vehicle data information with the second data time axis in the final slave vehicle data information to determine the missing time points in the slave vehicle data information as a set of data points to be supplemented.

[0101] S210. Determine the associated data point groups to be supplemented at adjacent times from the set of data points to be supplemented.

[0102] In this embodiment, adjacent time can be understood as two consecutive time points that are adjacent in time. A group of data points to be supplemented can be understood as a combination of two data points to be supplemented at adjacent time points.

[0103] Specifically, the processor can treat two data points in adjacent time periods within the set of data points to be supplemented as a group of associated supplementary data points.

[0104] S211. Connect the location points in the associated data point group to be supplemented, and generate a map to be divided based on the connection results and the preset fence range.

[0105] In this embodiment, a location point can be understood as its corresponding location information. A connection result can be understood as the result of connecting points along straight lines. A preset fence range can be understood as the range used to generate the map to be divided. The map to be divided can be understood as the range of the generated map.

[0106] Specifically, the processor can connect two location points in the associated group of data points to be supplemented, and determine the range from one location point to another according to the preset fence range based on the connection result between the two points, forming a map to be divided in a specific shape.

[0107] S212. Based on preset division conditions, the map to be divided into grids to obtain fence map information.

[0108] In this embodiment, the preset division conditions can be understood as conditions for equal area division, such as dividing into N1 grids, dividing into N2 grids, etc.

[0109] Specifically, the processor can divide the map to be divided into grids based on preset division conditions to obtain fence map information with the same number of grids as in the preset division conditions.

[0110] S213. Determine the predicted trajectory based on the final vehicle data in the data package.

[0111] In this embodiment, the predicted trajectory can be understood as the predicted vehicle movement trajectory.

[0112] Specifically, the processor can predict the vehicle trajectory in the set of supplementary data points based on information such as vehicle speed, heading angle, and map curvature in the final vehicle data in the data package, and obtain the predicted trajectory.

[0113] S214. Based on the area ratio of each grid cell in the fence map information according to the predicted trajectory, mark each grid cell to obtain the ratio mark set.

[0114] In this embodiment, the proportion marker set can be understood as a set used to characterize the proportion of the predicted trajectory to each grid cell.

[0115] Specifically, the processor can first determine the area proportion of each grid cell in the fence map information of the predicted trajectory, and then mark each grid cell according to the value corresponding to the area proportion to obtain the proportion mark set.

[0116] S215. Time-fill the data points to be supplemented corresponding to the target grids that meet the proportion conditions in the proportion mark set to obtain the final test data packet.

[0117] In this embodiment, the proportion condition can be understood as the condition used to determine the target grid of the trajectory path. The target grid can be understood as the determined trajectory path grid.

[0118] Specifically, the processor can compare each percentage marker in the percentage marker set with the percentage conditions, select the grid that meets the percentage conditions as the target grid, and fill the data points to be supplemented corresponding to the target grid according to the time point of the first data time axis of the corresponding main vehicle data information to obtain the final test data packet.

[0119] The technical solution of this invention determines target vehicle data and roadside data that match the test scenario generation conditions based on a pre-built database's data tag set, ensuring the adaptability of the obtained data to the set conditions. The target vehicle data and roadside data are cropped based on a target cropping duration matching the scenario, and then aligned and packaged to obtain data packets. Automatic judgment of the data point set to be supplemented in the data packets automatically identifies the data that needs supplementation. Fence map information is constructed by associating adjacent data points in the data point set to be supplemented. Based on the area ratio of each grid cell in the fence map information according to the predicted trajectory, a ratio marker set is determined. Target grid cells that meet the ratio conditions are time-filled to obtain the final test data packet. This ensures the authenticity and usability of the final test data and improves data adaptability.

[0120] For example, to facilitate understanding of the fence map information in this invention, Figure 3This is an example diagram of a fence map in a simulation data generation method provided in Embodiment 2 of the present invention. Figure 3 As shown, the straight lines in the figure are the connection results generated from the location points in the data point group to be supplemented. The 5×5 grid area in the figure is the fence map generated based on the connection results, the preset fence range, and the preset division conditions. The processor can determine the area ratio of each grid based on the predicted trajectory and mark each grid according to the corresponding number. That is, the number in each grid in the figure: mark 0 is recorded as the point not passed through, mark 1 is recorded as the range of the connection between the two location points is greater than 50%, which is reliable, mark 2 is recorded as the range of the connection between the two location points is less than 50%, which is unreliable, and mark 3 is recorded as the target grid. In the position surrounded by marks 0 and 2, 1 is the target grid.

[0121] Example 3

[0122] Figure 4 This is a schematic diagram of a simulation data generation device provided in Embodiment 3 of the present invention.

[0123] like Figure 4 As shown, the device includes:

[0124] Information acquisition module 41 is used to acquire test scenario generation conditions and search for target vehicle data information and roadside data information that meet the test scenario generation conditions based on the data tag set of the pre-built database.

[0125] The data packetization module 42 is used to process the target vehicle data information and the roadside data information in terms of duration and format to obtain a data packet.

[0126] The information determination module 43 is used to determine the set of data points to be supplemented in the data package, and to perform directed graph trajectory processing on the set of data points to be supplemented to obtain fence map information.

[0127] The test case generation module 44 is used to supplement the data point set to be supplemented based on the fence map information to obtain the final test data package.

[0128] The technical solution of this invention involves obtaining test scenario generation conditions, searching for target vehicle data and roadside data that meet these conditions based on a pre-built database's data tag set, processing the target vehicle data and roadside data for duration format to obtain data packets, determining the data point set to be supplemented within the data packets, and performing directed graph trajectory processing on this data point set to obtain fence map information, and supplementing the data point set according to the fence map information to obtain the final test data packet. By using a pre-built database constructed from real vehicle data, data matching the test scenario generation conditions is determined according to different dimensions based on the data tag set, and then data packets are assembled and supplemented to obtain the final test data packet. This ensures the authenticity and usability of the final test data and improves data adaptability.

[0129] Furthermore, the information acquisition module 41 is specifically used for:

[0130] Based on the data tag set of the pre-built database, determine the main vehicle data information that matches the test scenario generation conditions;

[0131] Search the pre-built database for slave vehicle data information associated with the master vehicle data information;

[0132] The master vehicle data information and the slave vehicle data information are used as the target vehicle data information that meets the test scenario generation conditions.

[0133] In the roadside data map of the pre-built database, determine the roadside data information corresponding to the location conditions in the test scenario generation conditions.

[0134] Optionally, the device also includes a database building module.

[0135] The database construction module includes:

[0136] The information acquisition unit is used to acquire the roadside location information of associated roadside equipment.

[0137] The map building unit is used to map the roadside location information to obtain a roadside data map.

[0138] The information receiving unit is used to receive the original vehicle driving information of the target vehicle that triggers the scene collection conditions. The original vehicle driving information includes the first original information of the target vehicle and the second original information of the associated vehicle.

[0139] The first determining unit is used to replace the identity information in the original vehicle driving information with a preset pointing value list to obtain the target vehicle driving information.

[0140] The second determining unit is used to perform tagging processing on the target vehicle driving information to obtain vehicle data information containing tags;

[0141] The database establishment unit is used to establish a pre-built database based on the data tag set composed of the tags, the vehicle data information, and the roadside data map.

[0142] Specifically, the second determining unit is used for:

[0143] Based on the scene acquisition conditions triggered by the target vehicle, determine the event type label;

[0144] The business scope to which the target vehicle's location belongs is determined based on a preset business scope area, as well as the area label of the business scope to which it belongs.

[0145] Based on the target vehicle's driving information, determine the road type label;

[0146] Obtain environmental information about the location of the target vehicle and determine scene labels;

[0147] Based on the event type label, the area label, the road type label, the scene label, and the target vehicle driving information, vehicle data information containing labels is generated.

[0148] Furthermore, the data packet assembly module 42 is specifically used for:

[0149] Based on the preset scene duration list, determine the target clipping duration that matches the target scene tag in the target vehicle data information;

[0150] Based on the target pruning duration, the target vehicle data is pruned to obtain intermediate vehicle data;

[0151] The intermediate master vehicle data information and intermediate slave vehicle data information in the intermediate vehicle data are aligned to obtain the final vehicle data;

[0152] The final vehicle data and the roadside data information are formatted according to a preset data format to obtain a data package.

[0153] Furthermore, the data package includes final master vehicle data information and final slave vehicle data information. Correspondingly, the information determination module 43 is specifically used for:

[0154] The first data timeline in the final master vehicle data information is compared with the second data timeline in the final slave vehicle data information to determine the set of data points to be supplemented in the slave vehicle data information.

[0155] Determine the associated data point groups to be supplemented at adjacent time points from the set of data points to be supplemented;

[0156] Connect the location points in the associated data point group to be supplemented, and generate a map to be divided based on the connection results and the preset fence range;

[0157] The map to be divided is divided into grids based on preset division conditions to obtain fence map information.

[0158] Furthermore, the use case generation module 44 is specifically used for:

[0159] The predicted trajectory is determined based on the final vehicle data in the data package;

[0160] Based on the area proportion of each grid cell in the fence map information according to the predicted trajectory, each grid cell is marked to obtain a proportion mark set;

[0161] Time-filling is performed on the data points to be supplemented corresponding to the target grids that meet the proportion conditions in the proportion mark set to obtain the final test data packet.

[0162] The simulation data generation device provided in this embodiment of the invention can execute the simulation data generation method provided in any embodiment of the invention, and has the corresponding functional modules and beneficial effects of the execution method.

[0163] Example 4

[0164] Figure 5 A schematic diagram of an electronic device 50 that can be used to implement embodiments of the present invention 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 processors, cellular phones, smartphones, wearable devices (e.g., helmets, glasses, watches, etc.), and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely illustrative and are not intended to limit the implementation of the invention described and / or claimed herein.

[0165] like Figure 5As shown, the electronic device 50 includes at least one processor 51 and a memory, such as a read-only memory (ROM) 52 and a random access memory (RAM) 53, communicatively connected to the at least one processor 51. The memory stores computer programs executable by the at least one processor. The processor 51 can perform various appropriate actions and processes based on the computer program stored in the ROM 52 or loaded into the RAM 53 from storage unit 58. The RAM 53 can also store various programs and data required for the operation of the electronic device 50. The processor 51, ROM 52, and RAM 53 are interconnected via a bus 54. An input / output (I / O) interface 55 is also connected to the bus 54.

[0166] Multiple components in electronic device 50 are connected to I / O interface 55, including: input unit 56, such as keyboard, mouse, etc.; output unit 57, such as various types of monitors, speakers, etc.; storage unit 58, such as disk, optical disk, etc.; and communication unit 59, such as network card, modem, wireless transceiver, etc. Communication unit 59 allows electronic device 50 to exchange information / data with other devices through computer networks such as the Internet and / or various telecommunications networks.

[0167] Processor 51 can be a variety of general-purpose and / or special-purpose processing components with processing and computing capabilities. Some examples of processor 51 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various special-purpose artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, a digital signal processor (DSP), and any suitable processor, controller, microcontroller, etc. Processor 51 performs the various methods and processes described above, such as simulation data generation methods.

[0168] In some embodiments, the simulation data generation method may be implemented as a computer program tangibly contained in a computer-readable storage medium, such as storage unit 58. In some embodiments, part or all of the computer program may be loaded and / or installed on electronic device 50 via ROM 52 and / or communication unit 59. When the computer program is loaded into RAM 53 and executed by processor 51, one or more steps of the simulation data generation method described above may be performed. Alternatively, in other embodiments, processor 51 may be configured to perform the simulation data generation method by any other suitable means (e.g., by means of firmware).

[0169] Various embodiments of the systems and techniques described above herein 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), systems-on-a-chip (SoCs), payload-programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various embodiments may include implementations in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which may be a dedicated or general-purpose programmable processor, capable of receiving data and instructions from a storage system, at least one input device, and at least one output device, and transmitting data and instructions to the storage system, the at least one input device, and the at least one output device.

[0170] Computer programs used to implement the methods of the present invention may be written in any combination of one or more programming languages. These computer programs may be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device, such that when executed by the processor, the computer programs cause the functions / operations specified in the flowcharts and / or block diagrams to be performed. The computer programs may be executed entirely on a machine, partially on a machine, or as a standalone software package, partially on a machine and partially on a remote machine, or entirely on a remote machine or server.

[0171] In the context of this invention, a computer-readable storage medium can be a tangible medium that may contain or store a computer program for use by or in conjunction with an instruction execution system, apparatus, or device. A computer-readable storage medium may include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination thereof. Alternatively, a computer-readable storage medium may be a machine-readable signal medium. More specific examples of machine-readable storage media include electrical connections based on one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fibers, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination thereof.

[0172] To provide interaction with a user, the systems and techniques described herein can be implemented on an electronic device 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 provides input to the electronic device. Other types of devices can also be used to provide interaction with the user; for example, 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 sound input, voice input, or tactile input).

[0173] The systems and technologies described herein can be implemented in computing systems that include backend components (e.g., as data servers), or computing systems that include middleware components (e.g., application servers), or computing systems that include frontend components (e.g., user computers with graphical user interfaces or web browsers through which users can interact with implementations of the systems and technologies described herein), or any combination of such backend, middleware, or frontend components. The components of the system can be interconnected via digital data communication of any form or medium (e.g., communication networks). Examples of communication networks include local area networks (LANs), wide area networks (WANs), blockchain networks, and the Internet.

[0174] A computing system can include clients and servers. Clients and servers are generally located far apart and typically interact through communication networks. The client-server relationship is created by computer programs running on the respective computers and having a client-server relationship with each other. The server can be a cloud server, also known as a cloud computing server or cloud host, which is a hosting product within the cloud computing service system to address the shortcomings of traditional physical hosts and VPS services, such as high management difficulty and weak business scalability.

[0175] It should be understood that the various forms of processes shown above can be used, with steps reordered, added, or deleted. For example, the steps described in this invention can be executed in parallel, sequentially, or in different orders, as long as the desired result of the technical solution of this invention can be achieved, and this is not limited herein.

[0176] The specific embodiments described above do not constitute a limitation on the scope of protection of this invention. Those skilled in the art should understand that various modifications, combinations, sub-combinations, and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of this invention should be included within the scope of protection of this invention.

Claims

1. A method for generating simulation data, characterized in that, include: Obtain the test scenario generation conditions, and search for target vehicle data information and roadside data information that meet the test scenario generation conditions based on the data tag set of the pre-built database; The target vehicle data information and the roadside data information are processed in a time-length format to obtain a data packet; the data packet includes the final master vehicle data information and the final slave vehicle data information. The first data timeline in the final master vehicle data information is compared with the second data timeline in the final slave vehicle data information to determine the set of data points to be supplemented in the slave vehicle data information. Determine the associated data point groups to be supplemented at adjacent time points from the set of data points to be supplemented; Connect the location points in the associated data point group to be supplemented, and generate a map to be divided based on the connection results and the preset fence range; The map to be divided is divided into grids based on preset division conditions to obtain fence map information; The predicted trajectory is determined based on the final vehicle data in the data package; Based on the area proportion of each grid cell in the fence map information of the predicted trajectory, each grid cell is marked to obtain a proportion mark set; wherein, the proportion mark set is a set used to characterize the proportion of the predicted trajectory to each grid cell; Time-filling is performed on the data points to be supplemented corresponding to the target grids that meet the proportion conditions in the proportion mark set to obtain the final test data packet.

2. The method according to claim 1, characterized in that, The process of searching for target vehicle data and roadside data that meet the test scenario generation conditions based on the data tag set of the pre-built database includes: Based on the data tag set of the pre-built database, determine the main vehicle data information that matches the test scenario generation conditions; Search the pre-built database for slave vehicle data information associated with the master vehicle data information; The master vehicle data information and the slave vehicle data information are used as the target vehicle data information that meets the test scenario generation conditions. In the roadside data map of the pre-built database, determine the roadside data information corresponding to the location conditions in the test scenario generation conditions.

3. The method according to claim 1, characterized in that, The steps for building the pre-built database include: Obtain the roadside location information of associated roadside equipment; The roadside location information is mapped to point locations to obtain a roadside data map; Receive the original vehicle driving information of the target vehicle that triggers the scene collection conditions, wherein the original vehicle driving information includes the first original information of the target vehicle and the second original information of the associated vehicle. The identity information in the original vehicle driving information is replaced by a preset list of pointing values ​​to obtain the target vehicle driving information; The target vehicle's driving information is tagged to obtain vehicle data information containing tags; A pre-built database is established based on the data tag set composed of the aforementioned tags, the vehicle data information, and the roadside data map.

4. The method according to claim 3, characterized in that, The step of tagging the target vehicle's driving information to obtain vehicle data information containing tags includes: Based on the scene acquisition conditions triggered by the target vehicle, determine the event type label; The business scope to which the target vehicle's location belongs is determined based on a preset business scope area, as well as the area label of the business scope to which it belongs. Based on the target vehicle's driving information, determine the road type label; Obtain environmental information about the location of the target vehicle and determine scene labels; Based on the event type label, the area label, the road type label, the scene label, and the target vehicle driving information, vehicle data information containing labels is generated.

5. The method according to claim 1, characterized in that, The process of processing the target vehicle data information and the roadside data information into a time-length format to obtain a data packet includes: Based on the preset scene duration list, determine the target clipping duration that matches the target scene tag in the target vehicle data information; Based on the target pruning duration, the target vehicle data is pruned to obtain intermediate vehicle data; The intermediate master vehicle data information and intermediate slave vehicle data information in the intermediate vehicle data are aligned to obtain the final vehicle data; The final vehicle data and the roadside data information are formatted according to a preset data format to obtain a data package.

6. A simulation data generation device, characterized in that, include: The information acquisition module is used to acquire the test scenario generation conditions and search for target vehicle data information and roadside data information that meet the test scenario generation conditions based on the data tag set of the pre-built database. The data packetization module is used to process the target vehicle data information and the roadside data information in a time-length format to obtain a data packet; the data packet includes the final master vehicle data information and the final slave vehicle data information. The information determination module is used to compare the first data time axis in the final master vehicle data information with the second data time axis in the final slave vehicle data information to determine the set of data points to be supplemented in the slave vehicle data information; and to determine the associated data point group to be supplemented at adjacent times from the set of data points to be supplemented. Connect the location points in the associated data point group to be supplemented, and generate a map to be divided based on the connection results and the preset fence range; The map to be divided is divided into grids based on preset division conditions to obtain fence map information; The test case generation module is used to determine the predicted trajectory based on the final vehicle data in the data package; mark each grid cell based on the area ratio of the predicted trajectory in the fence map information to obtain a ratio mark set; wherein, the ratio mark set is a set used to characterize the proportion of the predicted trajectory to each grid cell; and perform time filling on the data points to be supplemented corresponding to the target grid cells in the ratio mark set that meet the ratio conditions to obtain the final test data package.

7. An electronic device, characterized in that, The electronic device includes: At least one processor; and A memory communicatively connected to the at least one processor; wherein, The memory stores a computer program that can be executed by the at least one processor, the computer program being executed by the at least one processor to enable the at least one processor to perform the simulation data generation method according to any one of claims 1-5.

8. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer instructions that cause a processor to execute the simulation data generation method according to any one of claims 1-5.

Images