Urban traffic task scene generation method and system fused with multi-scale vehicles

Abstract

The invention relates to the technical field of urban traffic task scene simulation, and provides an urban traffic task scene generation method and system fused with multi-scale vehicles. The urban traffic task scene generation method fused with the multi-scale vehicles comprises the following steps: acquiring a natural language description corresponding to an urban traffic task scene demand of a user; calling a large language model to identify the natural language description, and converting the natural language description into intermediate expression; converting the intermediate expression into background traffic flow simulation parameters, and obtaining a traffic flow routing control file required by the macroscopic traffic simulation platform; and calling the macroscopic traffic simulation platform, operating the traffic flow routing control file in the macroscopic traffic simulation platform to obtain background traffic flow simulation data, calling the microscopic traffic simulation platform, and synchronously accessing the background traffic flow simulation data to the microscopic traffic simulation platform to generate an urban traffic task scene fusing macroscopic and microscopic multi-scale vehicles. The cost can be effectively reduced, and part of functional barriers between a macroscopic traffic simulation platform and a microscopic traffic simulation platform are broken through.

Description

Technical Field

[0001] This invention relates to the field of urban traffic task scenario simulation technology, and in particular to a method and system for generating urban traffic task scenarios that integrates multi-scale vehicles. Background Technology

[0002] The statements in this section are merely background information related to the present invention and do not necessarily constitute prior art.

[0003] Traffic simulation is a core technology for planning, design, operation management, safety assessment, and intelligent algorithm verification in the transportation field. Its core value relies on the "fidelity" and "diversity" of the simulation scenario in relation to the real traffic environment. With the rapid iteration of technologies such as intelligent connected vehicles (ICV) and vehicle-to-everything (V2X), the traffic scenarios considered have become increasingly complex. Traffic simulation scenarios are no longer traditional single-scale simulation control scenarios; many hybrid traffic task scenarios combining "background traffic flow + specific vehicle control" have emerged. Hybrid traffic scenarios integrate multi-scale simulation control, typically including macroscopic background traffic flow control and microscopic detailed control of specific vehicles such as acceleration, braking, and steering. Consequently, traditional single-scale traffic simulation scenario generation methods are no longer sufficient to meet the testing needs of complex dynamic traffic environments, and functional barriers exist between traffic simulation platforms of different scales.

[0004] Current traffic simulation platforms can only perform single-scale traffic simulations, which has many limitations. Macro-level traffic simulation platforms focus on large-scale traffic flow control, performing well in road network and traffic flow control, supporting the simulation and analysis of complex traffic systems, with strong compatibility with multi-source road network data, accurate traffic flow simulation, support for custom traffic models, and excellent open-source extensibility; however, they abstract vehicles too much, only abstracting them as cubes with limited functions, lacking the ability to simulate sensors and dynamic elements such as weather and lighting, and unable to finely simulate complex micro-level scenarios such as emergency braking or skidding in rain. Micro-level traffic simulation platforms focus on the high-fidelity characteristics of autonomous driving simulation, with low vehicle abstraction, including numerous sensors, and can simulate collision risks and handling responses in real driving in detail. They support dynamic weather, lighting changes, and complex urban environment modeling, with high simulation accuracy and detailed vehicle dynamics models, aiming to provide a high-fidelity simulation environment for the development, training, and verification of autonomous driving; however, their high level of detail in vehicle control simulation results in high costs. While microscopic traffic simulation platforms can simultaneously control multiple vehicles to form a background traffic flow, they consume a lot of resources, especially in the case of large maps where the background traffic flow can reach tens of thousands of vehicles. Furthermore, the background traffic flow does not require such detailed control, resulting in a significant waste of resources and making it difficult to construct large-scale complex road networks.

[0005] Macro-level and micro-level traffic simulation platforms are not universally compatible due to their different focuses. Their integration often encounters technical incompatibilities, such as incompatible vehicle types, different vehicle generation point positioning methods, and different vehicle route control methods. Existing platform integration interfaces also have many functional limitations, such as a limited number of parameters for generating existing road network files. Furthermore, with technological advancements, creating traffic simulation scenarios requires more specialized knowledge, gradually raising the barrier to entry for users. This makes it difficult to implement and popularize advanced technologies for non-professional users, and even poses challenges for experts unfamiliar with specific software systems.

[0006] Existing simulation work typically uses only a single platform, failing to combine the advantages of macro- and micro-level traffic simulation platforms for multi-scale vehicle abstraction and joint simulation. It also fails to incorporate natural language input processing on the basis of joint simulation. This results in significant limitations in application scenarios and user types, poor performance, slow simulation speed, and the need for substantial resources and manpower. Summary of the Invention

[0007] To address the aforementioned technical issues, this invention provides a method and system for generating urban traffic task scenarios that integrates multi-scale vehicles. This method can process users' natural language descriptions into corresponding simulation parameters. By integrating macroscopic traffic flow vehicles into a microscopic traffic simulation platform as background traffic flow in the scenario, it effectively reduces costs, breaks down some functional barriers between macroscopic and microscopic traffic simulation platforms, and lowers the technical threshold for non-professional users to generate scenarios using co-simulation tools.

[0008] To achieve the above objectives, the present invention adopts the following technical solution: The first aspect of the present invention provides a method for generating urban traffic task scenarios that integrates multi-scale vehicles.

[0009] In one or more embodiments, a method for generating urban traffic task scenarios by fusing multi-scale vehicles is provided, including: Obtain natural language descriptions of users' urban transportation task scenarios; The large language model is invoked to recognize the natural language description and convert it into an intermediate expression; the intermediate expression includes traffic flow origin information, directional moving traffic flow information, traffic flow size information, user's preferred vehicle type, and user's desired vehicle type adjustment strategy; The intermediate expression is converted into background traffic flow simulation parameters, and the traffic flow routing control file required by the macro traffic simulation platform is obtained. The system calls upon a macroscopic traffic simulation platform and runs a traffic flow routing control file within it to obtain background traffic flow simulation data. Simultaneously, it calls upon a microscopic traffic simulation platform and synchronously integrates the background traffic flow simulation data into the microscopic traffic simulation platform to generate an urban traffic task scenario that integrates macroscopic and microscopic multi-scale vehicles.

[0010] As one implementation method, in the process of converting intermediate expressions into background traffic flow simulation parameters: Based on the traffic flow origin point information in the intermediate representation, the road network information in the corresponding road network file is read using the API interface of the macro traffic simulation platform, and all road information in the entire map is returned. The API interface of the macro traffic simulation platform is called to query the road information of the entire map to see if the vehicle birth point information in the intermediate representation exists. If it exists, the road length and number of lanes are obtained from the road network file. Then, combined with the directional moving vehicle flow information, the preset vehicle length and the safety distance set at both ends of the road, the birth point of each destination vehicle is calculated.

[0011] As one implementation method, the formula corresponding to the spawn point of each destination vehicle is: ; ; in, This is an integer parameter used to finely adjust the number of vehicles generated based on the actual scene. The vehicle spawn point is the initial location of the vehicle's rear end.

[0012] As one implementation method, during the process of converting the intermediate expression into background traffic flow simulation parameters, other aimless roaming vehicles are generated based on the traffic flow size information in the intermediate expression, and these vehicles, along with the previously generated purposeful vehicles, are added to a preset vehicle list.

[0013] As one implementation method, a preset vehicle type ratio is calculated based on the user's preferred vehicle type in the intermediate expression and the user's desired vehicle type adjustment strategy, and vehicle types are assigned to vehicles in the traffic flow routing control file according to the adjusted vehicle type ratio.

[0014] As one implementation method, the formula for calculating the proportion of a certain vehicle type among all vehicle types after adjustment is as follows: .

[0015] As one implementation method, the background traffic flow simulation data of the macro traffic simulation platform is synchronously connected to the micro traffic simulation platform through the bridge-guided API interface between the macro traffic simulation platform and the micro traffic simulation platform. A start parameter is added to the bridge-guided API interface so that the vehicle simulation can start automatically after the macro traffic simulation platform is started.

[0016] A second aspect of the present invention provides a system for generating urban traffic task scenarios that integrates multi-scale vehicles.

[0017] In one or more embodiments, a system for generating urban traffic task scenarios that integrates multi-scale vehicles includes: The scenario requirement description module is used to obtain the natural language description of the user's urban traffic task scenario requirements; The intermediate expression generation module is used to call a large language model to recognize the natural language description and convert it into an intermediate expression; the intermediate expression includes traffic flow origin information, directional moving traffic flow information, traffic flow size information, user's preferred vehicle type and user's desired vehicle type adjustment strategy; The simulation parameter conversion module is used to convert intermediate expressions into background traffic flow simulation parameters and obtain the traffic flow routing control file required by the macro traffic simulation platform. The multi-scale fusion simulation module is used to call the macro-level traffic simulation platform and run the traffic flow routing control file in it to obtain background traffic flow simulation data. At the same time, it calls the micro-level traffic simulation platform and synchronously connects the background traffic flow simulation data to the micro-level traffic simulation platform to generate an urban traffic task scenario that integrates macro-level and micro-level multi-scale vehicles.

[0018] A third aspect of the present invention provides a computer-readable storage medium.

[0019] A computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps in the urban traffic task scene generation method fused with multi-scale vehicles as described above.

[0020] A fourth aspect of the present invention provides an electronic device.

[0021] An electronic device includes a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the program to implement the steps in the urban traffic task scene generation method fused with multi-scale vehicles as described above.

[0022] Compared with the prior art, the beneficial effects of the present invention are: This invention presents a method for generating urban traffic task scenarios that integrates multi-scale vehicles. It generates corresponding simulation scenarios based on user-defined natural language descriptions and automatically calls macro-level and micro-level traffic simulation platforms for scenario fusion. This fulfills the requirement of integrating macro-level traffic flow vehicles into the micro-level traffic simulation platform as background traffic flow in the scenario, thus participating in the generation of mixed traffic task scenarios. Through joint simulation using macro-level and micro-level traffic simulation platforms, low-cost macro-level traffic flow vehicles are integrated into the micro-level traffic simulation platform as background traffic flow in the scenario, effectively reducing costs and enabling the simulation scenario to simultaneously possess capabilities such as urban-level traffic flow control, sensor data control, road network planning, traffic signal optimization, and vehicle interaction, along with high-fidelity environmental effects. It supports complex scenario generation, achieving fully automatic API calls and platform startup, while modifying some bridging APIs to add self-starting functionality for scenario simulation. Furthermore, it generates relevant scenarios based on user-defined natural language descriptions, fully understanding user needs through a large model, eliminating the need for manual startup and debugging, effectively lowering the barrier to entry for non-professional users. Attached Figure Description

[0023] The accompanying drawings, which form part of this invention, are used to provide a further understanding of the invention. The illustrative embodiments of the invention and their descriptions are used to explain the invention and do not constitute an improper limitation of the invention.

[0024] Figure 1 This is a flowchart of the urban traffic task scene generation method integrating multi-scale vehicles according to an embodiment of the present invention; Figure 2 This is a schematic diagram illustrating the process of calculating the vehicle's birth point according to an embodiment of the present invention; Figure 3 This is a schematic diagram illustrating the process of adjusting the proportion of vehicle types based on user input according to an embodiment of the present invention; Figure 4 This is an example diagram of platform operation for generating background traffic flow based on a macroscopic traffic simulation platform, according to an embodiment of the present invention. Figure 5 Example 1 of the generated scene in this embodiment of the invention is shown in the figure. Figure 6 Example 2 of the scene generated in the embodiment of the present invention is shown; Figure 7 Example 3 of the generated scene in this embodiment of the invention is shown in Figure 3. Figure 8 Example 4 shows a scene generated by an embodiment of the present invention; Figure 9 This is an example illustration of a directional movement scene generated according to an embodiment of the present invention. Detailed Implementation

[0025] The present invention will be further described below with reference to the accompanying drawings and embodiments.

[0026] It should be noted that the following detailed description is illustrative and intended to provide further explanation of the invention. Unless otherwise specified, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention pertains.

[0027] It should be noted that the terminology used herein is for the purpose of describing particular embodiments only and is not intended to limit the scope of exemplary embodiments according to the invention. As used herein, the singular form is intended to include the plural form as well, unless the context clearly indicates otherwise. Furthermore, it should be understood that when the terms "comprising" and / or "including" are used in this specification, they indicate the presence of features, steps, operations, devices, components, and / or combinations thereof.

[0028] Figure 1 A flowchart of the urban traffic task scene generation method integrating multi-scale vehicles according to an embodiment of the present invention is provided. Figure 1 The urban traffic task scene generation method that integrates multi-scale vehicles in this embodiment may include the following steps: Step 1: Obtain the natural language description corresponding to the user's urban traffic task scenario requirements.

[0029] This step is... Figure 1 The input natural language description steps in the process.

[0030] Users describe the desired traffic flow conditions for the simulation scenario. The system provides various traffic simulation scenarios, traffic density preferences, vehicle types, and site parameters for user customization. For example, a user could describe the desired traffic flow conditions for the simulation scenario: "After get off work, people are leaving the central high-rise building (departure scenario), 8 cars went to residential buildings (directional movement scenario), 4 cars went to the shopping mall parking lot (directional movement scenario), traffic volume is moderate (traffic preference), and there are more trucks (vehicle type preference)." For example, based on the Town05 map, it provides three main scenarios (dispersal scenario, directional movement scenario, and congestion scenario), five vehicle density preferences (very small, small, medium, large, and very large, corresponding to different vehicle generation speeds), four vehicle types (cars, trucks, motorcycles, and bicycles; users can adjust the generation ratio of each type of vehicle according to their preferences. In this embodiment, through pre-search, the four vehicle types simultaneously supported by the macro-traffic simulation platform and the micro-traffic simulation platform are pre-defined and written into the slow_vehicles.add.xml attachment file, which developers can use directly. The vehicle types in this file support synchronous display on both platforms), seven vehicle colors, and more than ten location semantic definitions (central intersection, parking lot, etc.), etc., for users to customize. Figures 5-9 The examples in this document are all based on this embodiment. Developers can use this method to customize the scene parameter settings required by users.

[0031] Step 2: Call the large language model to recognize the natural language description and convert it into an intermediate expression; the intermediate expression includes traffic flow origin information, directional moving traffic flow information, traffic flow size information, user's preferred vehicle type and user's desired vehicle type adjustment strategy.

[0032] This step is... Figure 1 The intermediate expression generation step in the process.

[0033] This defines an intermediate representation from natural language to platform simulation parameters, used to tell the large language model which information to extract from user input. The intermediate representation comprises five main components: (1) Location: Traffic flow origin information, including a location name string.

[0034] (2) route_adjustment: Directional moving traffic information, including multiple 5-tuples, each 5-tuple is defined as<start_place,dest_place,count,speed_kmh,color> These describe the starting point, destination, number of vehicles, speed, and color of the directional moving traffic flow.

[0035] (3) traffic_flow: Traffic flow information, including a string describing the traffic flow size.

[0036] (4) preferred_vehicle_type: The type of vehicle that the user prefers to adjust.

[0037] (5) Adjustment: The strategy that users want to adjust their preferred vehicle type, that is, how users want to adjust the proportion of their preferred vehicle type, including a binary tuple.<type,amount> These describe the desired number of vehicles of this type, either more or less, or more or less.

[0038] Depending on the specific example, developers can add or remove parameter information based on this intermediate representation.

[0039] The prompt requires the large language model, acting as an expert in traffic simulation requirement analysis, to analyze the user's input according to the intermediate expression and provide an output example for the large language model to understand the output style. By incorporating this intermediate expression into the prompt, the large language model is invoked to recognize the user's natural language description and convert it into an intermediate expression of the background traffic flow scene, returning it as a JSON file. The large language model effectively increases the program's inclusiveness towards user natural language input, allowing users to input their requirements more freely, making the platform more accessible to users with diverse technical skills.

[0040] Step 3: Convert the intermediate expression into background traffic flow simulation parameters and obtain the traffic flow routing control file required by the macro traffic simulation platform.

[0041] This step is... Figure 1 The steps for converting background traffic flow simulation parameters.

[0042] This invention supports developers in defining traffic scenarios, classifying vehicles into purposeful vehicles (such as vehicles making exit actions, vehicles making directional movements, etc. in the example above) and other aimless wandering vehicles.

[0043] In one or more embodiments, during the process of converting intermediate representations into background traffic flow simulation parameters, such as Figure 2 As shown: Based on the traffic flow origin point information in the intermediate representation, the road network information in the corresponding road network file is read using the API interface of the macro traffic simulation platform, and all road information in the entire map (including each road ID, corresponding road length, road restricted vehicle type, road speed limit, etc.) is returned. The API interface of the macro traffic simulation platform is called to query the road information of the entire map to see if the vehicle birth point information in the intermediate representation exists. If it exists, the road length and number of lanes are obtained from the road network file. Then, combined with the directional moving vehicle flow information, the preset vehicle length and the safety distance set at both ends of the road, the birth point of each destination vehicle is calculated.

[0044] Before calling the API interface of the macro traffic simulation platform to query the road information of the entire map, the developer also needs to pre-define which road IDs correspond to the semantics of each location. The corresponding road IDs will be matched from the pre-defined information by querying the location information in the intermediate expression.

[0045] In this embodiment, the formula corresponding to the spawn point of each destination vehicle is: ; ; The vehicle spawn point refers to the initial location of the vehicle's rear end when it is first generated. This is an integer parameter used to finely adjust the number of vehicles generated based on the usage scenario. The safety distance between the two ends of the road is to prevent unmanageable congestion or collisions at intersections when the vehicle density is too high. Developers can assign a value to x according to the desired initial vehicle generation density. Generally, x=4, and the value of x can be appropriately increased when the road exceeds a set threshold.

[0046] By iterating through the number of vehicles to be generated, the distance between the specific spawn point of each vehicle on each road and the starting point of the road is calculated.

[0047] In other specific embodiments, during the process of converting the intermediate expression into background traffic flow simulation parameters, other aimless roaming vehicles are generated based on the traffic flow size information in the intermediate expression, and these vehicles, along with the previously generated purposeful vehicles, are added to a preset vehicle list.

[0048] For example, based on the intermediate representation, the information calculated earlier, and the simulation parameters of the macroscopic traffic simulation platform, preliminary vehicle trip information is generated, including vehicle birth time (automatically generated by API), birth location (calculated earlier), birth lane (randomly set by API), vehicle ID (customizable), vehicle start point (random), and vehicle end point (random).

[0049] The destination, color, speed, and other information of the vehicle being directed are modified based on the intermediate representation information. In the example above, the automatic compilation method will modify the destination, color, and speed information of the vehicle performing the directional movement action within the program based on the intermediate representation information.

[0050] Based on the user's preferred vehicle type adjustment strategy and the user's desired vehicle type proportion in the intermediate expression, calculate the preset vehicle type ratio, and assign vehicle types to the vehicles in the traffic flow routing control file according to the adjusted vehicle type ratio, such as... Figure 3 As shown.

[0051] For example, based on the trips information generated in the previous steps, the Duarouter API is called, and the generated trips information is passed in. The API automatically routes the data and outputs it as an XML file for later integration into the microscopic traffic simulation platform. The route generation is based on the breadth-first search method.

[0052] The formula for calculating the percentage of a certain vehicle type among all vehicle types after adjustment is as follows: .

[0053] Specifically, the change range needs to be preset, for example, "a little more" corresponds to a change range of "15%". The vehicle type percentage is the proportion of this vehicle type among the preset vehicle types.

[0054] Step 4: Call the macro-level traffic simulation platform and run the traffic flow routing control file in it to obtain background traffic flow simulation data. At the same time, call the micro-level traffic simulation platform and synchronously connect the background traffic flow simulation data to the micro-level traffic simulation platform to generate an urban traffic task scenario that integrates macro-level and micro-level multi-scale vehicles.

[0055] This step is... Figure 1 The steps for launching a joint simulation of macro and micro traffic simulation platforms.

[0056] The platform startup and simulation startup are integrated into the method program, eliminating the need for users to call the program via command line as required by the platform. The program achieves fully automated startup. In this part, the API of the macro-level traffic simulation platform is called to read the pre-written configuration file (containing the vehicle routing file generated in the previous steps, the pre-prepared road network information file, and other attachments) to obtain the generated background traffic flow simulation data and road network information. These vehicles are then run in the macro-level traffic simulation platform, and the simulation data such as the position, color, and speed of these vehicles are synchronously connected to the micro-level traffic simulation platform through the bridging API interface between the macro-level and micro-level traffic simulation platforms.

[0057] Considering that users need to manually set the simulation duration and click the start button every time the macro traffic simulation platform is started, the "start parameter" is supported by the macro traffic simulation platform itself, but not by the bridge approach API in the co-simulation; this embodiment of the invention adds the start parameter to the bridge approach API interface so that the macro traffic simulation platform can automatically start running vehicle simulation after startup.

[0058] After synchronization, users can observe in the window of the microscopic traffic simulation platform that the background traffic flow vehicles are moving according to the user's description, generating a corresponding background traffic flow scene. Therefore, using this method, users only need to add fine-grained control of specific vehicles to this microscopic traffic simulation platform to achieve a hybrid traffic task scenario that integrates "background traffic flow + specific vehicle control" across multiple scales. Figure 4 This is an example diagram of a background scene generated by a microscopic traffic simulation platform according to an embodiment of the present invention.

[0059] Figure 5 The generated exit scene is a display image showing "After visiting the company, everyone leaves from the central intersection. Ten cars go from the parking lot to the black high-rise building. There are a lot of vehicles, mostly sedans." Figure 6 The generated scene depicts "After get off work, people leave from the black high-rise building, with 10 cars leaving the parking lot and residential area. There are a lot of vehicles, mostly sedans." Figure 7 The generated scene depicts "After get off work, everyone leaves the factory. Ten cars leave the factory for the residential area. There are a lot of vehicles, mostly cars." Figure 8 The generated exit scene is a display image showing "After watching the movie, everyone leaves the parking lot. Ten cars go from the parking lot to the black high-rise building. There are a lot of vehicles, mostly sedans." Figure 9 This is an example illustration of a directional movement scenario generated in an embodiment of the present invention (after get off work, people leave the parking lot, and 10 cars go from the parking lot to the residential area; the number of vehicles is large, with more cars).

[0060] This invention calculates and adjusts pre-set information based on intermediate representations, then automatically calls various API interfaces of the macro-traffic simulation platform to read road network information and generate routing files. Finally, by modifying some program content of the bridge approach API, the self-starting of the macro-traffic simulation platform is achieved, reducing user complexity.

[0061] The urban traffic task scenario generation method of this invention, which integrates multi-scale vehicles, combines the powerful semantic understanding capabilities of a large language model. By fusing macroscopic traffic flow vehicles into a microscopic traffic simulation platform as the background traffic flow in the scenario, it breaks down the functional barriers between macroscopic and microscopic platforms. It integrates the core advantages of "macroscopic traffic flow control" and "microscopic fine vehicle detail control" of the aforementioned platforms. Subsequently, only specific fine vehicle control needs to be added to the microscopic traffic simulation platform to effectively realize the simulation of mixed traffic task scenarios. It provides city-level traffic flow regulation capabilities while restoring high-fidelity environment and sensor data. It also supports complex scenarios such as road network planning, traffic signal optimization, and vehicle interaction, providing underlying methodological support for the simulation of complex scenarios with cross-domain integration. It is reshaping the technical paradigm of intelligent transportation research and providing indispensable simulation methodological support for the deep integration of smart cities and autonomous driving in the future.

[0062] In one or more embodiments, a multi-scale vehicle-integrated urban traffic task scene generation system is also provided, which can be implemented in software. The multi-scale vehicle-integrated urban traffic task scene generation system includes the following software modules: The scenario requirement description module is used to obtain the natural language description of the user's urban traffic task scenario requirements; The intermediate expression generation module is used to call a large language model to recognize the natural language description and convert it into an intermediate expression; the intermediate expression includes traffic flow origin information, directional moving traffic flow information, traffic flow size information, user's preferred vehicle type and user's desired vehicle type adjustment strategy; The simulation parameter conversion module is used to convert intermediate expressions into background traffic flow simulation parameters and obtain the traffic flow routing control file required by the macro traffic simulation platform. The multi-scale fusion simulation module is used to call the macro-level traffic simulation platform and run the traffic flow routing control file in it to obtain background traffic flow simulation data. At the same time, it calls the micro-level traffic simulation platform and synchronously connects the background traffic flow simulation data to the micro-level traffic simulation platform to generate an urban traffic task scenario that integrates macro-level and micro-level multi-scale vehicles.

[0063] It should be noted that each module in the urban traffic task scene generation system that integrates multi-scale vehicles in this embodiment corresponds one-to-one with each step in the urban traffic task scene generation method that integrates multi-scale vehicles in the above embodiment, and their specific implementation processes are the same, so they will not be repeated here.

[0064] The structure of an electronic device according to an embodiment of the present invention is described in detail below. An electronic device includes at least one processor, a memory, a user interface, and at least one network interface. The various components in the multi-scale vehicle urban traffic task scene generation system are coupled together via a bus system. It can be understood that the bus system is used to realize the connection and communication between these components. In addition to a data bus, the bus system also includes a power bus, a control bus, and a status signal bus. The user interface may include a display, keyboard, mouse, trackball, click wheel, buttons, a touchpad, or a touch screen, etc.

[0065] It is understood that the memory can be volatile memory or non-volatile memory, or both. The memory in this embodiment of the invention is capable of storing data to support the operation of the terminal. Examples of this data include any computer programs used to operate on the terminal, such as operating systems and applications. The operating system includes various system programs, such as the framework layer, core library layer, driver layer, etc., used to implement various basic services and handle hardware-based tasks. Applications can include various applications.

[0066] In some embodiments, the urban traffic task scene generation system integrating multi-scale vehicles provided in this invention can be implemented using a combination of hardware and software. As an example, the system can be a processor in the form of a hardware decoding processor, programmed to execute the urban traffic task scene generation method integrating multi-scale vehicles provided in this invention. For instance, the processor in the form of a hardware decoding processor can employ one or more application-specific integrated circuits (ASICs), DSPs, programmable logic devices (PLDs), complex programmable logic devices (CPLDs), field-programmable gate arrays (FPGAs), or other electronic components.

[0067] As an example, a processor can be an integrated circuit chip with signal processing capabilities, such as a general-purpose processor, a digital signal processor (DSP), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc., where a general-purpose processor can be a microprocessor or any conventional processor, etc.

[0068] As an example of the hardware implementation of the urban traffic task scene generation system integrating multi-scale vehicles provided in this embodiment of the invention, the device provided in this embodiment of the invention can be directly executed by a processor in the form of a hardware decoding processor. For example, it can be executed by one or more application-specific integrated circuits (ASICs), DSPs, programmable logic devices (PLDs), complex programmable logic devices (CPLDs), field-programmable gate arrays (FPGAs), or other electronic components to implement the urban traffic task scene generation method integrating multi-scale vehicles provided in this embodiment of the invention.

[0069] The memory in this embodiment of the invention is used to store various types of data to support the operation of the urban traffic task scenario generation system that integrates multi-scale vehicles, or to store data for execution. Figure 1The program code for the method shown. Examples of this data include: any executable instructions for operation on a multi-scale vehicle-integrated urban traffic task scene generation system, such as executable instructions that can be included in the program implementing the multi-scale vehicle-integrated urban traffic task scene generation method of this embodiment of the invention.

[0070] Specifically, according to embodiments of this application, the processes described above with reference to the flowcharts can be implemented as computer software programs. For example, embodiments of this application include a computer program product comprising a computer program carried on a computer-readable medium, the computer program including functions for executing... Figure 1 The program code for the method shown. In such an embodiment, the computer program can be downloaded and installed from a network via a communication component, and / or installed from a removable medium. When the computer program is executed by the central processing unit, it performs the various functions defined in the apparatus of this application.

[0071] This invention is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It will be understood that each block of the flowchart illustrations and / or block diagrams, as well as combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart. Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0072] The above are merely preferred embodiments of the present invention and are not intended to limit the present invention. Various modifications and variations can be made to the present invention by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the present invention should be included within the scope of protection of the present invention.

Claims

1. A method for generating urban traffic task scenarios integrating multi-scale vehicles, characterized in that, include: Obtain natural language descriptions of users' urban transportation task scenarios; The large language model is invoked to recognize the natural language description and convert it into an intermediate expression; the intermediate expression includes traffic flow origin information, directional moving traffic flow information, traffic flow size information, user's preferred vehicle type, and user's desired vehicle type adjustment strategy; The intermediate expression is converted into background traffic flow simulation parameters, and the traffic flow routing control file required by the macro traffic simulation platform is obtained. The system calls upon a macroscopic traffic simulation platform and runs a traffic flow routing control file within it to obtain background traffic flow simulation data. Simultaneously, it calls upon a microscopic traffic simulation platform and synchronously integrates the background traffic flow simulation data into the microscopic traffic simulation platform to generate an urban traffic task scenario that integrates macroscopic and microscopic multi-scale vehicles.

2. The method for generating urban traffic task scenarios by integrating multi-scale vehicles as described in claim 1, characterized in that, In the process of converting intermediate expressions into background traffic flow simulation parameters: Based on the traffic flow origin point information in the intermediate representation, the road network information in the corresponding road network file is read using the API interface of the macro traffic simulation platform, and all road information in the entire map is returned. The API interface of the macro traffic simulation platform is called to query the road information of the entire map to see if the vehicle birth point information in the intermediate representation exists. If it exists, the road length and number of lanes are obtained from the road network file. Then, combined with the directional moving vehicle flow information, the preset vehicle length and the safety distance set at both ends of the road, the birth point of each destination vehicle is calculated.

3. The method for generating urban traffic task scenarios by integrating multi-scale vehicles as described in claim 2, characterized in that, The formula corresponding to the spawn point of each destination vehicle is: ； ； in, It is an integer parameter used to finely adjust the number of vehicles according to requirements.

4. The method for generating urban traffic task scenarios by integrating multi-scale vehicles as described in claim 1, characterized in that, In the process of converting intermediate expressions into background traffic flow simulation parameters, other aimless roaming vehicles are generated based on the traffic flow size information in the intermediate expressions, and these vehicles, along with the previously generated purposeful vehicles, are added to a preset vehicle list.

5. The method for generating urban traffic task scenarios by integrating multi-scale vehicles as described in claim 1, characterized in that, Based on the user's preferred vehicle type and the user's desired vehicle type adjustment strategy in the intermediate expression, calculate the preset vehicle type ratio, and assign vehicle types to the vehicles in the traffic flow routing control file according to the adjusted vehicle type ratio.

6. The method for generating urban traffic task scenarios by integrating multi-scale vehicles as described in claim 5, characterized in that, The formula for calculating the percentage of a certain vehicle type among all vehicle types after adjustment is as follows: 。 7. The method for generating urban traffic task scenarios by integrating multi-scale vehicles as described in claim 1, characterized in that, By utilizing the bridge-guide API interface between the macro-traffic simulation platform and the micro-traffic simulation platform, the background traffic flow simulation data of the macro-traffic simulation platform is synchronously connected to the micro-traffic simulation platform. A start parameter is added to the bridge-guide API interface so that the vehicle simulation can automatically start running after the macro-traffic simulation platform is started.

8. A system for generating urban traffic task scenarios integrating multi-scale vehicles, characterized in that, The urban traffic task scene generation method based on any one of claims 1-7 includes: The scenario requirement description module is used to obtain the natural language description of the user's urban traffic task scenario requirements; The intermediate expression generation module is used to call a large language model to recognize the natural language description and convert it into an intermediate expression; the intermediate expression includes traffic flow origin information, directional moving traffic flow information, traffic flow size information, user's preferred vehicle type and user's desired vehicle type adjustment strategy; The simulation parameter conversion module is used to convert intermediate expressions into background traffic flow simulation parameters and obtain the traffic flow routing control file required by the macro traffic simulation platform. The multi-scale fusion simulation module is used to call the macro-level traffic simulation platform and run the traffic flow routing control file in it to obtain background traffic flow simulation data. At the same time, it calls the micro-level traffic simulation platform and synchronously connects the background traffic flow simulation data to the micro-level traffic simulation platform to generate an urban traffic task scenario that integrates macro-level and micro-level multi-scale vehicles.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the program is executed by the processor, it implements the steps in the method for generating urban traffic task scenarios by fusing multi-scale vehicles as described in any one of claims 1-7.

10. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, When the processor executes the program, it implements the steps in the urban traffic task scene generation method that integrates multi-scale vehicles as described in any one of claims 1-7.

Images