Road scene generation method and device, electronic equipment and storage medium
Generate configuration files of road scenes through natural language description text and configure generation algorithm parameters, which solves the problem of high-quality road scene generation and high-quality road scene generation and modification experience in the prior art, and realizes a user-friendly scene generation and modification experience.
Patent Information
- Application Number
- CN202410985131.3
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-07-22
- Publication Date
- 2024-11-26
AI Technical Summary
In the prior art, the method of generating high-quality road scenarios requires developers to understand complex algorithm details and programming capabilities, resulting in high development complexity and low efficiency, especially when facing complex road networks and dynamic environments. .
By obtaining the user's natural language description text, using the large language model to extract key information to generate the configuration file of the road scene, and generating algorithm parameters based on the configuration file, generating the corresponding road scene.
Without understanding technical details, users can generate and modify road scenarios through natural language input, reducing modification costs, improving design and adjustment flexibility, simplifying the interaction between users and generation algorithms, and improving user experience.
Smart Images

Figure CN119027601A_ABST
Abstract
Description
Technical Field
[0001] The present disclosure relates to the field of computer technology, and in particular to a method, device, electronic device, and storage medium for generating a road scene. Background Art
[0002] With the continuous development of the gaming industry and digital twin technology, the realism and complexity of digital scenes are increasing, and users' requirements for a better visual experience are also rising. High-quality road scenes not only enhance user immersion but also significantly improve the overall performance of games or digital twin simulation applications. Therefore, how to quickly produce high-quality road scenes is a pressing issue. A common solution is to use procedural generation methods to create road scenes. Algorithms automatically generate large amounts of scene content in a short period of time, greatly improving development efficiency. However, previous procedural generation methods often require the design of specific algorithms and constraints tailored to different needs. Developers need to fully understand the algorithm details and translate the design into specific algorithm programs and parameters. This not only increases development complexity but also places high demands on developers' programming skills and proficiency in game engine usage. Designing and implementing appropriate generation algorithms becomes more difficult and time-consuming when faced with complex road networks, diverse terrains, and dynamically changing environments. Summary of the Invention
[0003] The present disclosure provides a method, device, electronic device and storage medium for generating a road scene, so as to at least solve the above technical problems existing in the prior art.
[0004] According to a first aspect of the present disclosure, a method for generating a road scene is provided, the method comprising: obtaining natural language description text input by a user, the natural language description text representing the construction requirements of the road scene; extracting key information from the natural language description text through a large language model to generate a configuration file for the road scene; and configuring parameters in a road generation algorithm based on the configuration file to generate a road scene corresponding to the natural language description text.
[0005] In one possible implementation, before obtaining the natural language description text input by the user, the method further includes: obtaining scene information input by the user, inputting the scene information into a large language model to preprocess the large language model, and generating knowledge base information of the large language model, wherein the scene information is in a natural language form and includes the coordinates of landmarks and preset parsing rules.
[0006] In one possible implementation, the natural language description text includes road location information and road condition information; the extracting key information of the natural language description text through the large language model to generate a configuration file of the road scene includes: extracting the road location information in the natural language description text through the large language model, and determining the coordinate information of the starting point and end point of the road in the road scene based on the knowledge base information of the large language model; extracting the road condition information in the natural language description text through the large language model, and determining the specific parameters and decoration conditions of the road in the road scene based on the knowledge base information of the large language model; generating the configuration file of the road scene according to the coordinate information of the starting point and end point of the road, the specific parameters and decoration conditions of the road.
[0007] In one possible implementation, the parameters in the road generation algorithm are configured based on the configuration file to generate a road scene corresponding to the natural language description text, including: generating a spline curve corresponding to the starting point and end point based on the coordinate information of the road starting point and end point in the configuration file and a first road generation algorithm; generating a road scene corresponding to the natural language description text based on the spline curve, the specific parameters and decoration of the road in the configuration file and a second road generation algorithm.
[0008] In one embodiment, the method further includes: displaying the road scene; obtaining natural language correction text input by the user, wherein the natural language correction text represents the user's correction requirements for the displayed road scene; and correcting the road scene based on the natural language correction text.
[0009] According to a second aspect of the present disclosure, a device for generating a road scene is provided, comprising: an acquisition module for acquiring a natural language description text input by a user, wherein the natural language description text represents the construction requirements of the road scene; a first generation module for extracting key information of the natural language description text through a large language model to generate a configuration file for the road scene; and a second generation module for configuring parameters in a road generation algorithm based on the configuration file to generate a road scene corresponding to the natural language description text.
[0010] In one embodiment, the device also includes: a processing module for obtaining scene information input by the user before obtaining the natural language description text input by the user, inputting the scene information into the large language model to preprocess the large language model, and generating knowledge base information of the large language model, wherein the scene information is in natural language form and includes the coordinates of the landmark and preset parsing rules.
[0011] In one possible implementation, the natural language description text includes road location information and road condition information; the first generation module includes: a first determination submodule, which extracts the road location information in the natural language description text through the large language model, and determines the coordinate information of the starting point and end point of the road in the road scene based on the knowledge base information of the large language model; a second determination submodule, which is used to extract the road condition information in the natural language description text through the large language model, and determine the specific parameters and decoration conditions of the road in the road scene based on the knowledge base information of the large language model; a generation submodule, which is used to generate a configuration file of the road scene based on the coordinate information of the starting point and end point of the road, the specific parameters and decoration conditions of the road.
[0012] In one embodiment, the second generation module is specifically used to generate a spline curve corresponding to the start point and end point based on the coordinate information of the road start point and end point in the configuration file and the first road generation algorithm; and generate a road scene corresponding to the natural language description text based on the spline curve, the specific parameters and decoration conditions of the road in the configuration file and the second road generation algorithm.
[0013] In one embodiment, the device also includes: a display module for displaying the road scene; a correction module for obtaining natural language correction text input by a user, wherein the natural language correction text represents the user's correction requirements for the displayed road scene; and correcting the road scene based on the natural language correction text.
[0014] According to a third aspect of the present disclosure, there is provided an electronic device, including:
[0015] at least one processor; and
[0016] a memory communicatively connected to the at least one processor; wherein,
[0017] The memory stores instructions that can be executed by the at least one processor. The instructions are executed by the at least one processor to enable the at least one processor to perform the method described in the present disclosure.
[0018] According to a fourth aspect of the present disclosure, a non-transitory computer-readable storage medium storing computer instructions is provided, wherein the computer instructions are used to cause the computer to execute the method described in the present disclosure.
[0019] The present disclosure discloses a method, device, electronic device, and storage medium for generating a road scene. The method first obtains a natural language description text input by a user that represents the requirements for constructing a road scene. Key information from the natural language description text is then extracted using a large language model to generate a configuration file for the road scene. Finally, parameters in a road generation algorithm are configured based on the configuration file to generate a road scene corresponding to the natural language description text. Using this method, users can generate corresponding road scenes by inputting natural language without having to understand complex technical details. The natural language-based control method is more user-friendly and convenient to use. When modifying a road scene, users only need to adjust the natural language input content without having to change the underlying algorithm parameters. This significantly reduces modification costs, increases design and adjustment flexibility, simplifies the interaction between the user and the generation algorithm, and enhances the user experience. Users can generate and modify road scenes more intuitively and conveniently, improving design efficiency.
[0020] It should be understood that the contents described in this section are not intended to identify the key or important features of the embodiments of the present disclosure, nor are they intended to limit the scope of the present disclosure. Other features of the present disclosure will become readily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS
[0021] The above and other objects, features and advantages of the exemplary embodiments of the present disclosure will become readily understood by reading the detailed description below with reference to the accompanying drawings, in which several embodiments of the present disclosure are shown by way of example and not limitation, wherein:
[0022] In the drawings, the same or corresponding reference numerals denote the same or corresponding parts.
[0023] Figure 1 The schematic diagram shows the implementation process of a method for generating a road scene according to an embodiment of the present disclosure. Figure 1 ;
[0024] Figure 2 The schematic diagram shows the implementation process of a method for generating a road scene according to an embodiment of the present disclosure. Figure 2 ;
[0025] Figure 3 The schematic diagram shows the implementation process of a method for generating a road scene according to an embodiment of the present disclosure. Figure 3 ;
[0026] Figure 4a A schematic diagram showing a method for generating a road scene according to an embodiment of the present disclosure Figure 1 ;
[0027] Figure 4b A schematic diagram showing a method for generating a road scene according to an embodiment of the present disclosure Figure 2 ;
[0028] Figure 5 A schematic diagram of a module of a device for generating a road scene according to an embodiment of the present disclosure is shown;
[0029] Figure 6 A schematic diagram of the structure of an electronic device according to an embodiment of the present disclosure is shown. DETAILED DESCRIPTION
[0030] To make the purposes, features, and advantages of the present disclosure more apparent and understandable, the technical solutions in the embodiments of the present disclosure will be clearly and completely described below in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present disclosure, not all of them. All other embodiments obtained by those skilled in the art based on the embodiments of the present disclosure without creative work shall fall within the scope of protection of the present disclosure.
[0031] Figure 1 The schematic diagram shows the implementation process of a method for generating a road scene according to an embodiment of the present disclosure. Figure 1 ,include:
[0032] Step 101: Obtain a natural language description text input by a user, where the natural language description text represents the construction requirements of a road scene.
[0033] The user first enters a natural language description text that can represent the construction requirements of the road scene to be generated, and the scene construction requirements described by the user in natural language can be obtained in the form of a dialog box.
[0034] Step 102: extract key information from the natural language description text using a large language model to generate a configuration file for the road scene.
[0035] After obtaining the natural language description text input by the user, the key information of the natural language description text is extracted through a large language model. The large language model is a model that has been trained with a large amount of data to enable it to understand and generate natural language and other types of content to perform various tasks. The large language model actually selected in this application is GPT-4o. GPT-4o is a multimodal large model that supports any combination of text, audio and image input, and can generate any combination of text, audio and image output. The large language model can be called in the Unreal Engine by calling the OpenAI API through a script to conduct natural language question and answer and interact with it. The large language model recognizes the input natural language description text and obtains key information. The key information refers to the information related to the road scene that the user expects to generate, and the key information is integrated to generate a configuration file for the road scene.
[0036] Step 103 : configuring parameters in the road generation algorithm based on the configuration file to generate a road scene corresponding to the natural language description text.
[0037] The parameters in the road generation algorithm are configured according to the key information of the road scene in the configuration file, and finally a road scene corresponding to the natural language description text is generated.
[0038] This application first obtains a user-entered natural language description of the road scene's construction requirements. It then uses a large language model to extract key information from the natural language description and generate a configuration file for the road scene. Finally, based on the configuration file, the parameters in the road generation algorithm are configured to generate the road scene corresponding to the natural language description. Using this method, users can generate the corresponding road scene by inputting natural language, without having to understand complex technical details. This natural language-based control method is more user-friendly and convenient, improving the user experience.
[0039] In one possible implementation, before obtaining the natural language description text input by the user, the method also includes: obtaining scene information input by the user, inputting the scene information into the large language model to preprocess the large language model, and generating knowledge base information of the large language model, wherein the scene information is in natural language form, and the scene information includes the coordinates of the landmark and preset parsing rules.
[0040] Before obtaining the natural language description text input by the user, the large language model needs to be preprocessed, that is, the large language model needs to be trained. The scene information input by the user is obtained, and the scene information includes environmental information for generating the road scene, such as information about landmarks included in the environment, location coordinate information of entrances and exits, etc., and the knowledge base information of the large language model is generated according to the scene information input by the user, wherein the obtained scene information is also input by the user in the form of natural language. In addition to the coordinate information of the landmarks in the scene, the knowledge base information of the large language model also includes parsing rules. The parsing rules can be customized according to actual conditions, and may include requirements for the content, form, and order of the information output by the large language model. The output of the large language model is used to generate a configuration file so that the road generation algorithm generates the corresponding road scene according to the configuration file.
[0041] In one embodiment, Figure 2 As shown, the natural language description text includes road location information and road condition information. The key information of the natural language description text is extracted through the large language model to generate a configuration file of the road scene, including:
[0042] Step 201: extracting road location information from a natural language description text using a large language model, and determining the coordinate information of the start and end points of the road in the road scene based on the knowledge base information of the large language model;
[0043] Step 202: extracting road condition information from the natural language description text using the large language model, and determining specific parameters and decoration conditions of the road in the road scene based on the knowledge base information of the large language model;
[0044] Step 203: Generate a configuration file of the road scene based on the coordinate information of the road start point and end point, the specific parameters of the road and the decoration conditions.
[0045] The natural language description text includes road location information and road condition information. The road location information refers to the locations of the starting point and end point of the road. The location information can be specific coordinate information or the name of a landmark in the scene; the road condition information refers to the conditions of the roadbed, pavement, structures and ancillary facilities in the road scene.
[0046] The large language model extracts road location information from the natural language description text entered by the user. This road location information is then matched with the large language model's knowledge base to determine the coordinate information of the road's starting and ending points within the road scene. The road location information described in the natural language description text entered by the user can include various description forms. After processing by the large language model, the road location information can be output in a form corresponding to a preset parsing rule. In this application, the preset parsing rule corresponding to the road location information is to output the coordinate information of the road's starting and ending points within the road scene.
[0047] The large language model extracts road condition information from the natural language description text entered by the user. This information is then matched against the large language model's knowledge base to determine the specific parameters and decoration of the road in the scene. After processing by the large language model, the road condition information is output in a format that corresponds to pre-set parsing rules.
[0048] The obtained coordinate information of the road start and end points, the specific parameters of the road and the decoration conditions are integrated to generate a configuration file of the road scene.
[0049] In one embodiment, configuring parameters in a road generation algorithm based on a configuration file to generate a road scene corresponding to a natural language description text includes:
[0050] Generate a spline curve corresponding to the start point and the end point based on the coordinate information of the road start point and the end point in the configuration file and the first road generation algorithm;
[0051] Based on the spline curve, specific parameters and decoration conditions of the road in the configuration file and the second road generation algorithm, a road scene corresponding to the natural language description text is generated.
[0052] The configuration file contains the coordinate information of the road's start and end points, as well as the specific parameters and installation conditions of the road. First, based on the coordinate information of the road's start and end points in the configuration file and the first road generation algorithm, a spline curve corresponding to the start and end points is generated. Specifically, the coordinate information of the start and end points is input into the Unreal Editor's Get Spline Data blueprint through a custom script. Get Spline Data generates the spline curve corresponding to the start and end points based on the coordinates of the road's start and end points and the NavMesh. The main blueprint nodes called are FindPath to Location Synchronously and Add Spline Point.
[0053] Based on the generated spline curves corresponding to the starting and end points, the specific parameters and decoration of the road, and the second road generation algorithm, a road scene corresponding to the natural language description text is generated. Specifically, a custom script is used to call the Draw Road blueprint based on the Unreal Engine's Procedural Content Generation Framework (PCG) plug-in. The blueprint generates path lines in the terrain system according to the generated spline curves, fills the lines with corresponding materials, and adjusts the angle and position of the road so that it is correctly attached to different surface shapes. The specific functions used are Get Mesh Length, Calculate Spacing, Road Distribution, Add Road Segments, etc.
[0054] In addition, static decorations on the road can be configured through the static mesh generator in the PCG plug-in, such as roadside fences, street lights, and signposts. The generator corresponding to each decoration has a parameter as input, which is the value output by the large language model after extracting and matching the natural language description text; dynamic decorations such as cars randomly distributed on the road can be generated through the dynamic mesh generator in the PCG plug-in. Similarly, the corresponding generator also has a parameter as input, which is the value output by the large language model. For decorations that only describe the quantity but not the specific location, such as the specific location of the car on the road, the distribution of defects in the road material, etc., the second road generation algorithm can randomly distribute the positions according to the unit length of the road, and fill the corresponding decorations into the road scene in proportion to the actual generated length.
[0055] In one embodiment, Figure 3 As shown, the method further includes:
[0056] Step 301, displaying a road scene;
[0057] Step 302: Obtain natural language correction text input by the user, where the natural language correction text represents the user's correction requirements for the displayed road scene;
[0058] Step 303: Correct the road scene based on the natural language correction text.
[0059] The road scene will be generated in the Unreal Editor, and the generated road scene can be displayed through the Unreal Editor or a display device. The user can view the specific situation of the generated road scene in the Unreal Editor or the display device. If there is a deviation between the generated road scene and the road scene expected by the user or the user wants to add new requirements to the generated road scene, the user can describe the content that needs to be corrected or added in the form of natural language, that is, natural language correction text, and the natural language correction text represents the user's correction requirements for the displayed road scene. After obtaining the natural language correction text, the key information in the natural language correction text can be extracted through the large language model to generate a new road scene configuration file, and a corrected road scene corresponding to the natural language correction text is generated based on the new configuration file. In addition, the corrected road scene can be displayed until a road scene that meets the user's requirements is generated.
[0060] Figure 4a and Figure 4b A schematic diagram of a scene showing a method for generating a road scene according to an embodiment of the present disclosure is shown.
[0061] First, the user's road design scenario information is input into the large language model in natural language format for preprocessing. For example, if the user inputs "Building A (0, 0), Building B (1925, 2034), Building C (-2327, 8485), the model will return the corresponding value based on the input." The preset parsing rules are: 1. The start and end points of the road are expressed as building coordinates, and the coordinates of the start and end points are output; 2. The road decoration conditions, including material (0 for dilapidated, 10 for new, and values between 0-10 for other conditions), fences (1 for fenced, 0 for no fence), and streetlights (1 for streetlights, 0 for no streetlights); 3. The number of vehicles on the road; 4. Each rule is output in one line.
[0062] The natural language description text entered by the user in the dialog box is obtained as "a road from building A to building B, the road is a single lane wide two-way road, there are railings around the road, there are no street lights, the road material is brand new, and there are 5 vehicles on the road." This natural language description text indicates the construction requirements of the road scene. After parsing the above natural language description text through the large language model, the parsing results obtained are: 1. The starting point of the road is building A, coordinates (0, 0), and the end point of the road is building B, coordinates (1925, 2034); 2. The decoration of the road: material: brand new (10), fence: fence (1), street light: no street light (0); 3. The number of vehicles on the road: 5. Therefore, the generated configuration file can be in the form of:
[0063] {
[0064] (0, 0), (1925, 2034)
[0065] 10, 1, 0 5
[0067] }.
[0068] The first line of the configuration file contains the coordinates of the start and end points of the road in the road scene. The second and third lines contain the specific parameters and decoration of the road in the road scene. Based on the content of the first line of the configuration file and the first road generation algorithm, a spline curve from building A to building B, i.e., from coordinates (0, 0) to (1925, 2034), can be generated, such as Figure 4a As shown in the figure, a spline curve is generated from a cube to a cuboid, where the cube represents building A (0, 0) and the cylinder represents building B (1925, 2034). Based on the generated spline curve, the contents of the second and third lines of the configuration file and the second road generation algorithm, a road scene corresponding to the natural language description text is generated, as shown in the figure. Figure 4b As shown in Figure 2, the generated road scene.
[0069] Figure 5 A module schematic diagram of a device for generating a road scene according to an embodiment of the present disclosure is shown.
[0070] See also Figure 5 According to the second aspect of the present disclosure, a device for generating a road scene is provided, the device comprising: an acquisition module 501, for acquiring a natural language description text input by a user, where the natural language description text represents the construction requirements of the road scene; a first generation module 502, for extracting key information of the natural language description text through a large language model and generating a configuration file of the road scene; a second generation module 503, for configuring parameters in a road generation algorithm based on the configuration file and generating a road scene corresponding to the natural language description text.
[0071] In one embodiment, the device also includes: a processing module 504, which is used to obtain scene information input by the user before obtaining the natural language description text input by the user, input the scene information into the large language model to preprocess the large language model, and generate knowledge base information of the large language model. The scene information is in natural language form, and the scene information includes the coordinates of the landmark and preset parsing rules.
[0072] In one embodiment, the natural language description text includes road location information and road condition information; the first generation module 502 includes: a first determination submodule 5021, which extracts the road location information in the natural language description text through a large language model, and determines the coordinate information of the starting point and end point of the road in the road scene based on the knowledge base information of the large language model; a second determination submodule 5022, which is used to extract the road condition information in the natural language description text through a large language model, and determine the specific parameters and decoration conditions of the road in the road scene based on the knowledge base information of the large language model; a generation submodule 5023, which is used to generate a configuration file of the road scene based on the coordinate information of the starting point and end point of the road, the specific parameters and decoration conditions of the road.
[0073] In one embodiment, the second generation module 503 is specifically used to generate a spline curve corresponding to the start point and the end point based on the coordinate information of the road start point and the end point in the configuration file and the first road generation algorithm; and generate a road scene corresponding to the natural language description text based on the spline curve, the specific parameters and decoration conditions of the road in the configuration file and the second road generation algorithm.
[0074] In one embodiment, the device also includes: a display module 505 for displaying a road scene; a correction module 506 for obtaining a natural language correction text input by a user, the natural language correction text representing the user's correction requirements for the displayed road scene; and correcting the road scene based on the natural language correction text.
[0075] According to an embodiment of the present disclosure, the present disclosure also provides an electronic device and a readable storage medium.
[0076] Figure 6A schematic block diagram of an example electronic device 600 that can be used to implement embodiments of the present disclosure is shown. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as personal digital assistants, cellular phones, smartphones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions are provided as examples only and are not intended to limit the implementation of the present disclosure described and / or claimed herein.
[0077] like Figure 6 As shown, the device 600 includes a computing unit 601, which can perform various appropriate actions and processes according to a computer program stored in a read-only memory (ROM) 602 or a computer program loaded from a storage unit 608 into a random access memory (RAM) 603. Various programs and data required for the operation of the device 600 can also be stored in the RAM 603. The computing unit 601, the ROM 602, and the RAM 603 are connected to each other via a bus 604. An input / output (I / O) interface 605 is also connected to the bus 604.
[0078] Various components in device 600 are connected to I / O interface 605, including an input unit 606, such as a keyboard, mouse, etc.; an output unit 607, such as various types of displays, speakers, etc.; a storage unit 608, such as a magnetic disk, optical disk, etc.; and a communication unit 609, such as a network card, modem, wireless communication transceiver, etc. The communication unit 609 allows device 600 to exchange information / data with other devices via a computer network such as the Internet and / or various telecommunication networks.
[0079] The computing unit 601 can be any general-purpose and / or specialized processing component with processing and computing capabilities. Some examples of the computing unit 601 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various specialized artificial intelligence (AI) computing chips, various computing units running machine learning model algorithms, a digital signal processor (DSP), and any suitable processor, controller, microcontroller, etc. The computing unit 601 performs the various methods and processes described above, such as a method for generating a road scene. For example, in some embodiments, a method for generating a road scene can be implemented as a computer software program tangibly embodied in a machine-readable medium, such as the storage unit 608. In some embodiments, part or all of the computer program can be loaded and / or installed onto the device 600 via the ROM 602 and / or the communication unit 609. When the computer program is loaded into the RAM 603 and executed by the computing unit 601, one or more steps of the method for generating a road scene described above can be performed. Alternatively, in other embodiments, the computing unit 601 can be configured to perform the method for generating a road scene by any other suitable means (e.g., via firmware).
[0080] Various embodiments of the systems and techniques described 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), system-on-chip systems (SOCs), programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various embodiments can include being implemented in one or more computer programs that are executable and / or interpreted on a programmable system that includes at least one programmable processor, which can be a special purpose or general purpose programmable processor that can receive data and instructions from a storage system, at least one input device, and at least one output device, and transmit data and instructions to the storage system, the at least one input device, and the at least one output device.
[0081] The program code for implementing the method of the present disclosure can be written in any combination of one or more programming languages. These program codes can be provided to a processor or controller of a general-purpose computer, a special-purpose computer, or other programmable data processing device so that when the program code is executed by the processor or controller, the functions / operations specified in the flow chart and / or block diagram are implemented. The program code can be executed entirely on the machine, partially on the machine, as a stand-alone software package, partially on the machine and partially on a remote machine, or entirely on a remote machine or server.
[0082] In the context of the present disclosure, a machine-readable medium can be a tangible medium that can contain or store a program for use by or in conjunction with an instruction execution system, device or equipment. A machine-readable medium can be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium can include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or equipment, or any suitable combination of the foregoing. A more specific example of a machine-readable storage medium can include an electrical connection based on one or more lines, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.
[0083] To provide interaction with a user, the systems and techniques described herein can be implemented on a computer having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and pointing device (e.g., a mouse or trackball) through which the user can provide input to the computer. Other types of devices can also be used to provide interaction with the user; for example, the feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including acoustic input, voice input, or tactile input).
[0084] The systems and techniques described herein can be implemented in a computing system that includes back-end components (e.g., as a data server), or a computing system that includes middleware components (e.g., an application server), or a computing system that includes front-end components (e.g., a user computer having a graphical user interface or a web browser through which a user can interact with implementations of the systems and techniques described herein), or a computing system that includes any combination of such back-end components, middleware components, or front-end components. The components of the system can be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include a local area network (LAN), a wide area network (WAN), and the Internet.
[0085] A computer system may include a client and a server. The client and server are generally remote from each other and typically interact through a communication network. The client-server relationship arises from computer programs running on the respective computers and having a client-server relationship with each other. The server may be a cloud server, a server in a distributed system, or a server integrated with a blockchain.
[0086] It should be understood that the various forms of the processes shown above can be used to reorder, add, or delete steps. For example, the steps described in this disclosure can be performed in parallel, sequentially, or in a different order, as long as the desired results of the technical solutions disclosed in this disclosure can be achieved. This is not a limitation herein.
[0087] Furthermore, the terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of technical features being referred to. Thus, a feature defined as "first" or "second" may explicitly or implicitly include at least one such feature. Throughout the present disclosure, "plurality" means two or more, unless otherwise specifically defined.
[0088] The above description is merely a specific embodiment of the present disclosure, but the scope of protection of the present disclosure is not limited thereto. Any changes or substitutions that can be easily conceived by a person skilled in the art within the technical scope disclosed in this disclosure should be included in the scope of protection of the present disclosure. Therefore, the scope of protection of the present disclosure should be based on the scope of protection of the claims.
Claims
1. A method for generating a road scene, characterized in that: The method comprises: Acquire a natural language description text input by a user, wherein the natural language description text represents a construction requirement of a road scene; Extracting key information of the natural language description text through a large language model to generate a configuration file of the road scene; Parameters in a road generation algorithm are configured based on the configuration file to generate a road scene corresponding to the natural language description text.
2. The method according to claim 1, characterized in that Before obtaining the natural language description text input by the user, the method further includes: The scene information input by the user is obtained, and the scene information is input into a large language model to preprocess the large language model to generate knowledge base information of the large language model, wherein the scene information is in a natural language form and includes the coordinates of a landmark and a preset parsing rule.
3. The method according to claim 1, characterized in that The natural language description text includes road location information and road condition information; The step of extracting key information of the natural language description text by using a large language model to generate a configuration file of the road scene includes: Extracting the road location information in the natural language description text through the large language model, and determining the coordinate information of the starting point and the end point of the road in the road scene based on the knowledge base information of the large language model; Extracting the road condition information in the natural language description text through the large language model, and determining the specific parameters and decoration conditions of the road in the road scene based on the knowledge base information of the large language model; A configuration file of the road scene is generated according to the coordinate information of the starting point and the end point of the road, the specific parameters and the decoration of the road.
4. The method according to claim 3, characterized in that The configuring parameters in the road generation algorithm based on the configuration file to generate a road scene corresponding to the natural language description text includes: Based on the coordinate information of the road start point and the end point in the configuration file and the first road generation algorithm, generate a spline curve corresponding to the start point and the end point; A road scene corresponding to the natural language description text is generated based on the spline curve, specific parameters and decoration conditions of the road in the configuration file, and a second road generation algorithm.
5. The method according to claim 1, characterized in that The method further comprises: displaying the road scene; Acquire a natural language correction text input by a user, wherein the natural language correction text represents the user's correction requirement for the displayed road scene; The road scene is corrected based on the natural language correction text.
6. A device for generating a road scene, characterized in that: The device comprises: An acquisition module, used to acquire a natural language description text input by a user, wherein the natural language description text represents a construction requirement of a road scene; A first generating module, configured to extract key information of the natural language description text through a large language model to generate a configuration file of the road scene; The second generation module is used to configure parameters in the road generation algorithm based on the configuration file to generate a road scene corresponding to the natural language description text.
7. The device according to claim 6, characterized in that The device also includes: A processing module is used to obtain scene information input by a user before obtaining a natural language description text input by the user, input the scene information into a large language model to preprocess the large language model, and generate knowledge base information of the large language model, wherein the scene information is in a natural language form and includes the coordinates of a landmark and preset parsing rules.
8. The device according to claim 6, characterized in that The natural language description text includes road location information and road condition information; The first generating module comprises: A first determination submodule extracts the road location information in the natural language description text through the large language model, and determines the coordinate information of the starting point and the end point of the road in the road scene based on the knowledge base information of the large language model; A second determination submodule is used to extract the road condition information in the natural language description text through the large language model, and determine the specific parameters and decoration conditions of the road in the road scene based on the knowledge base information of the large language model; The first generating submodule is used to generate a configuration file of the road scene according to the coordinate information of the starting point and the end point of the road, the specific parameters and the decoration of the road.
9. An electronic device, characterized in that: include: at least one processor; as well as a memory communicatively connected to the at least one processor; wherein, The memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to perform the method according to any one of claims 1 to 5.
10. A non-transitory computer-readable storage medium storing computer instructions, characterized in that: The computer instructions are used to cause the computer to execute the method according to any one of claims 1-5.
Citation Information
Cited By
Platform equipment access method, system and equipment based on intelligent agent and storage medium
CN120750963A
Three-dimensional scene logic skeleton generation method and device, electronic equipment and medium
CN121600226A
