Fluid scene generation method and device, electronic equipment and storage medium

Abstract

The embodiment of the invention discloses a fluid scene generation method and device, electronic equipment and a storage medium. The method comprises the steps that under the condition that scene description information input by a user is received, a fluid simulation scene and a main body shape model are generated according to the scene description information on the basis of a pre-trained large language model; inputting the fluid simulation scene and the main body shape model into preset simulation software to obtain a simulation result of the fluid scene; and displaying the simulation result through a preset interactive interface to complete the simulation process of the fluid scene. On the basis, the user only needs to input the scene description information, the fluid scene can be generated, the purpose of simulation is achieved, the user does not need to grasp fluid related knowledge, the threshold of fluid simulation is lowered, and the process of fluid simulation is simplified.

Description

Technical Field

[0001] The embodiments of the present application relate to the field of simulation technology, and in particular to a fluid scene generation method, device, electronic device and storage medium. Background Art

[0002] With the development of computer technology, computers are often used in scenarios such as industrial design, scientific research, and engineering applications, and simulation technology is used to build the models involved. Especially for fluid models, in order to study the fluid, special fluid simulation software is used to simulate the behavior of the fluid and its interaction with the solid.

[0003] When using fluid simulation software for fluid simulation, users are required to have certain professional knowledge, including the basics of fluid mechanics, software operation skills, etc. This raises the threshold for using fluid simulation. If non-professional users need to perform fluid simulation in their work or life scenarios, it is difficult to achieve. Summary of the invention

[0004] The embodiments of the present application provide a fluid scene generation method, device, electronic device and storage medium to reduce the level of expertise required in the fluid simulation process and improve the universality of fluid simulation.

[0005] In a first aspect, an embodiment of the present application provides a method for generating a fluid scene, the method comprising:

[0006] When receiving scene description information input by a user, generating a fluid simulation scene and a main body shape model according to the scene description information based on a pre-trained large language model;

[0007] Input the fluid simulation scene and the main body shape model into the preset simulation software to obtain the simulation result of the fluid scene;

[0008] The simulation results are displayed through a preset interactive interface to complete the simulation process of the fluid scene.

[0009] In a second aspect, an embodiment of the present application provides a fluid scene generation device, the device comprising:

[0010] A generation module, for generating a fluid simulation scene and a main body shape model according to the scene description information based on a pre-trained large language model when receiving the scene description information input by the user;

[0011] A simulation module is used to input the fluid simulation scene and the main body shape model into the preset simulation software to obtain the simulation result of the fluid scene;

[0012] The display module is used to display the simulation results through a preset interactive interface to complete the simulation process of the fluid scene.

[0013] In a third aspect, an embodiment of the present application further provides an electronic device, the electronic device comprising:

[0014] one or more processors;

[0015] a storage device for storing one or more programs,

[0016] When one or more programs are executed by one or more processors, the one or more processors implement the fluid scene generation method provided in any embodiment of the present application.

[0017] In a fourth aspect, an embodiment of the present application further provides a computer-readable storage medium having a computer program stored thereon, wherein the program, when executed by a processor, implements a fluid scene generation method as provided in any embodiment of the present application.

[0018] The technical solution of the embodiment of the present application, upon receiving the scene description information input by the user, generates a fluid simulation scene and a main body shape model based on a pre-trained large language model according to the scene description information; inputs the fluid simulation scene and the main body shape model into the preset simulation software to obtain the simulation result of the fluid scene; and displays the simulation result through a preset interactive interface to complete the simulation process of the fluid scene. Based on this, the user only needs to input the scene description information to complete the generation of the fluid scene and achieve the purpose of simulation, without the need for the user to master fluid-related knowledge, which lowers the threshold of fluid simulation and simplifies the process of fluid simulation. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] Figure 1 A schematic diagram of a flow chart of a method for generating a fluid scene provided in Embodiment 1 of the present application;

[0020] Figure 2 A schematic diagram of the structure of a fluid scene generation device provided in Embodiment 2 of the present application;

[0021] Figure 3 A schematic diagram of the structure of an electronic device provided in Example 3 of the present application. DETAILED DESCRIPTION

[0022] The present application will be further described in detail below in conjunction with the accompanying drawings and embodiments. It is to be understood that the specific embodiments described herein are only used to explain the present application, rather than to limit the present application. It should also be noted that, for ease of description, only the parts related to the present application, rather than all structures, are shown in the accompanying drawings.

[0023] Embodiment 1

[0024] Figure 1A flow chart of a method for generating a fluid scene according to the first embodiment of the present invention is shown in FIG. Figure 1 As shown, the fluid scene generation method provided in this embodiment can be applied to a fluid scene generation platform mounted on a device with data processing capabilities such as a computer, and can be used in conjunction with some application software to achieve a better experience. Specifically, the method may include the following steps:

[0025] Step 101: upon receiving scene description information input by a user, generate a fluid simulation scene and a main body shape model according to the scene description information based on a pre-trained large language model.

[0026] In this step, the user can enter scene description information in a preset interactive interface. The preset interactive interface can be written in Gradio but is not limited to other similar tools. Subsequent modification, selection, display and other processes can be performed on the preset interactive interface.

[0027] It should be noted that the scene description information is text information or picture information of a fluid scene described by the user. Taking text information as an example, the scene description information may include scene information and subject information. In a specific example, the scene description information may be a stone falling into a pool from a height of h with an initial velocity of 0 and an acceleration of g.

[0028] The pre-trained large language model can analyze the scene description information, mainly to extract the scene features and generate prompt words corresponding to the shape of the subject. In order to speed up the simulation, this embodiment generates the fluid simulation scene and the subject shape model separately and in parallel.

[0029] Specifically, the pre-trained large language model may include a first large language model and a second large language model, the first large language model is used to analyze and obtain scene features, and the second large language model is used to analyze and obtain shape generation prompt words.

[0030] In this step, the scene description information can be input into the first language model to obtain scene features, and at least one simulation scene example can be extracted from a preset physical simulation scene library based on the scene features; then a simulation scene example is determined from the at least one simulation scene example as a fluid simulation scene.

[0031] The scene feature may be a feature word. Taking the above example as an example, the scene features that can be obtained include falling, pool, height, speed, acceleration, etc. At least one simulation scene example can be matched based on these scene features.

[0032] Specifically, the scene features may be matched with the simulation features of each simulation scene example in a preset physical simulation scene library; and then the simulation scene examples satisfying the preset matching conditions are extracted.

[0033] It should be noted that the simulation features can be directly reflected in the name of the simulation scene example. That is to say, when the physical simulation scene library is initially created, each simulation scene example can be named and its corresponding simulation features can be included in the naming. For example, for a simulation scene example that includes a pool, falling and splashing water, etc., the name of the simulation scene example can be "Pool Falling and Splashing Water".

[0034] When matching, the feature hit rate of each simulation scene example can be determined. It should be noted that the feature hit rate refers to the percentage of the number of scene features contained in the simulation features of a simulation scene example to the total number of scene features. This percentage is the feature hit rate of the simulation scene example.

[0035] In a specific example, the scene features of the aforementioned example band are dropping, pool, height, speed, and acceleration. The total number of scene features is 5. The name of a certain simulation scene example is "Falling into the Pool and Splashing Water", which contains the two scene features of "pool" and "dropping". Therefore, the feature hit rate of this simulation scene example is 2 / 5=40%.

[0036] In addition, in order to further improve the matching accuracy, the present embodiment may further refine the process of determining whether the simulation feature contains the scene feature. For example, a feature similarity determination model may be pre-trained, and the scene feature and the simulation feature may be input into the feature similarity determination model to obtain similar features and the number of similar features output by the model.

[0037] It should be noted that the similarity determination of the feature similarity determination model is based not only on the text similarity of words, but also on the similarity of the modeling features corresponding to the words. For example, pool and swimming pool can be determined as similar features.

[0038] The training process can rely on a large number of modeling-related feature words, so that the trained feature similarity determination model has the above capabilities. The specific training process can refer to the relevant technology and will not be repeated here.

[0039] After obtaining the feature hit rate of each simulation scenario example, a preset number of simulation scenario examples with the highest feature hit rate may be determined as at least one simulation scenario example in this step.

[0040] In addition, in order to better meet the user's intention, this embodiment can display at least one simulation scene example as an option and obtain the user's scene selection information; determine a simulation scene example from at least one simulation scene example as a fluid simulation scene based on the scene selection information.

[0041] Specifically, the at least one simulation scenario example obtained above can be displayed in the above preset interactive interface, and an interactive selection box can be set for each displayed simulation scenario example. The user completes the input of the scenario selection information by checking the interactive selection box.

[0042] The scene selection information includes the check information of the interactive selection box, so as to determine the simulation scene example corresponding to the interactive selection box, and then determine the simulation scene example as a fluid simulation scene.

[0043] In addition, for the main shape model, the scene description information can be input into the second largest language model to obtain shape generation prompt words, and the main shape model is generated according to the shape generation prompt words.

[0044] It should be noted that since fluid simulation usually involves physical subjects, in order to build the subject shape model, it is necessary to obtain the corresponding shape generation prompt words. Shape generation prompt words are usually words that describe the shape of the subject. The technology of generating the subject shape model based on words refers to the technology of converting text descriptions into 3D models using natural language processing and 3D generation models. It combines multiple technologies such as language understanding, 2D image generation and 3D modeling, and can automatically create 3D objects or scenes that meet the description based on the user's text input. The core of this technology is to understand the text semantics and extract key information, convert semantic information into geometric shapes and textures in 3D space, and generate high-quality, physically compliant 3D models.

[0045] Specifically, the technology of text-to-3D generation allows users to use natural language to describe the objects they want to create, which is then automatically converted into a 3D model by the system. This approach greatly simplifies tasks that originally required professional knowledge to complete. For example, Shap-E, an advanced 3D model generation technology developed by OpenAI, can quickly generate 3D models based on text descriptions or 2D images. It uses implicit representations to directly generate parameters of implicit functions, which can be rendered into texture meshes and neural radiation fields (NeRFs), thereby achieving diverse and realistic three-dimensional asset generation. Shap-E is able to generate complex 3D models in a short time. Depending on the configuration and hardware, the generation time can range from a few seconds to a few minutes. For example, in some tests, it may take about 28.3 seconds to generate a 3D model through text, while it may take 17.2 seconds to generate through images. In addition, the 3D models generated by Shap-E have good details and quality and can be used in professional-level applications.

[0046] In addition, the present embodiment can also modify the main body shape model. Specifically, the main body shape model can be demonstrated through a preset interactive interface, and modification information input by the user can be obtained; the main body shape model can be modified according to the modification information.

[0047] This modification process can also use the aforementioned text-to-3D model technology, which will not be described in detail here.

[0048] Step 102: input the fluid simulation scene and the main body shape model into a preset simulation software to obtain a simulation result of the fluid scene.

[0049] In this step, the scene features may include scene simulation features and material types. The simulation parameters of the fluid simulation scene may be configured according to the scene simulation features and material types, and the configured fluid simulation scene and the main body shape model may be simulated and calculated to obtain the simulation result of the fluid scene.

[0050] Among them, this step can modify the simulation parameters of the matched simulation scene configuration according to the scene features extracted from the scene description information, that is, the scene simulation features and material types. Finally, the modified fluid simulation scene and the main body shape model are input into the preset simulation software for simulation. The simulation software will read the simulation scene configuration file for calculation, and finally obtain the simulation results for post-processing.

[0051] The above-mentioned process of modifying simulation parameters is similar to template instantiation, and the extracted information is used to instantiate the parameters of the simulation scenario configuration file. Please refer to the relevant technology, which will not be described here.

[0052] In a specific example, this step can be based on but is not limited to the capability support of the PartoX simulation software. Specifically, as a tool that supports particle method fluid simulation, the core feature of the PartoX simulation software is to insert a solid model and use the surface mesh (triangle or polygon) of the solid model to capture the characteristics of fluid motion. This design allows users to focus on the study of fluid behavior without worrying about the impact of the solid model on the simulation process. PartoX supports surface meshes of solid models of arbitrary resolution and is suitable for a variety of discrete particle methods, providing powerful simulation support for the present invention.

[0053] Since the fluid simulation scene and main shape model on which this step is based contain the content required by the simulation software for simulation, mainly scene simulation characteristics, material types and main shape models, the simulation software can perform simulation calculations based on these contents to obtain simulation results.

[0054] Step 103: Display the simulation results through a preset interactive interface to complete the simulation process of the fluid scene.

[0055] In this step, the simulation results can be displayed in the form of a simulation video on a preset interactive interface.

[0056] In a specific example, the implementation of this step can be but is not limited to the advantages of creating a Gradio front-end page and the ability of Paraview to visualize the results.

[0057] Among them, Gradio is a tool for quickly creating web applications, especially suitable for building user interfaces for users to enter text descriptions and receive generated 3D objects. The advantage of Gradio is that it simplifies the front-end development process, allowing developers to focus on the implementation of core functions rather than the details of the interface. With Gradio, users can intuitively see the connection between the input text and the output results, making the whole process transparent and easy to use.

[0058] Paraview is a powerful visualization tool that can be used to display and analyze complex data sets, including large amounts of data generated by fluid simulation. Through Paraview, users can easily view information such as fluid velocity distribution and pressure distribution, and better understand fluid behavior through different views and color coding. In addition, Paraview also supports exporting data in multiple formats, which is convenient for users to further analyze or integrate with other software. The present invention uses Paraview to export simulation results as videos to more intuitively display the simulation effect.

[0059] It should be noted that the above specific example is only an example of this embodiment, and this embodiment can also be implemented based on other similar means.

[0060] In this embodiment, when the scene description information input by the user is received, a fluid simulation scene and a main body shape model are generated according to the scene description information based on a pre-trained large language model; the fluid simulation scene and the main body shape model are input into the preset simulation software to obtain the simulation result of the fluid scene; the simulation result is displayed through a preset interactive interface to complete the simulation process of the fluid scene. Based on this, the user only needs to input the scene description information to complete the generation of the fluid scene and achieve the purpose of simulation. The user does not need to master the relevant knowledge of fluids, which lowers the threshold of fluid simulation and simplifies the process of fluid simulation.

[0061] Embodiment 2

[0062] Figure 2This is a schematic diagram of the structure of a fluid scene generation device provided in the second embodiment of the present application. The fluid scene generation device provided in the embodiment of the present application can execute the fluid scene generation method provided in any embodiment of the present application, and has the corresponding functional modules and beneficial effects of the execution method. The device can be implemented in software and / or hardware, such as Figure 2 As shown, the fluid scene generation device specifically includes: an optimization direction generation module 201, a simulation module 202, and a display module 203.

[0063] Wherein, the generation module is used to generate a fluid simulation scene and a main body shape model according to the scene description information based on a pre-trained large language model when receiving the scene description information input by the user;

[0064] A simulation module is used to input the fluid simulation scene and the main body shape model into the preset simulation software to obtain the simulation result of the fluid scene;

[0065] The display module is used to display the simulation results through a preset interactive interface to complete the simulation process of the fluid scene.

[0066] Furthermore, the generation module is specifically used for:

[0067] Inputting the scene description information into the first language model to obtain scene features, and extracting at least one simulation scene example from a preset physical simulation scene library according to the scene features;

[0068] Determine a simulation scene example from at least one simulation scene example as a fluid simulation scene;

[0069] The scene description information is input into the second largest language model to obtain shape generation prompt words, and the main shape model is generated according to the shape generation prompt words.

[0070] Furthermore, the generation module is specifically used for:

[0071] Displaying at least one simulation scenario example as an option and obtaining scenario selection information from a user;

[0072] A simulation scene example is determined from at least one simulation scene example as a fluid simulation scene according to the scene selection information.

[0073] Furthermore, the device is also specifically used for:

[0074] Through the preset interactive interface, the main shape model is demonstrated and the modification information input by the user is obtained;

[0075] Modify the main shape model according to the modification information.

[0076] Furthermore, the scene features include scene simulation features and material types;

[0077] The simulation module is specifically used for:

[0078] The simulation parameters of the fluid simulation scene are configured according to the scene simulation characteristics and the material type, and the configured fluid simulation scene and the main body shape model are simulated and calculated to obtain the simulation result of the fluid scene.

[0079] Furthermore, the generation module is specifically used for:

[0080] Matching the scene features with the simulation features of each simulation scene example in the preset physical simulation scene library;

[0081] Extract simulation scenario examples that meet preset matching conditions.

[0082] Furthermore, the display module is specifically used for:

[0083] The simulation results are displayed in the form of simulation videos on a preset interactive interface.

[0084] Embodiment 3

[0085] Figure 3 A schematic diagram of the structure of an electronic device provided in Embodiment 3 of the present application is shown in FIG. Figure 3 As shown, the electronic device includes a processor 310, a memory 320, an input device 330 and an output device 340; the number of the processor 310 in the electronic device can be one or more. Figure 3 A processor 310 is taken as an example; the processor 310, the memory 320, the input device 330 and the output device 340 in the electronic device can be connected via a bus or other means. Figure 3 The example of connecting through bus is taken in the following.

[0086] The memory 320 is a computer-readable storage medium that can be used to store software programs, computer executable programs and modules, such as program instructions / modules corresponding to the fluid scene generation method in the embodiment of the present invention. The processor 310 executes various functional applications and data processing of the electronic device by running the software programs, instructions and modules stored in the memory 320, that is, to implement the above-mentioned fluid scene generation method:

[0087] When receiving scene description information input by a user, generating a fluid simulation scene and a main body shape model according to the scene description information based on a pre-trained large language model;

[0088] Input the fluid simulation scene and the main body shape model into the preset simulation software to obtain the simulation result of the fluid scene;

[0089] The simulation results are displayed through a preset interactive interface to complete the simulation process of the fluid scene.

[0090] Further, when the scene description information input by the user is received, the fluid simulation scene and the main body shape model are generated according to the scene description information based on the pre-trained large language model, including:

[0091] Inputting the scene description information into the first language model to obtain scene features, and extracting at least one simulation scene example from a preset physical simulation scene library according to the scene features;

[0092] Determine a simulation scene example from at least one simulation scene example as a fluid simulation scene;

[0093] The scene description information is input into the second largest language model to obtain shape generation prompt words, and the main shape model is generated according to the shape generation prompt words.

[0094] Further, determining a simulation scene example from at least one simulation scene example as a fluid simulation scene includes:

[0095] Displaying at least one simulation scenario example as an option and obtaining scenario selection information from a user;

[0096] A simulation scene example is determined from at least one simulation scene example as a fluid simulation scene according to the scene selection information.

[0097] Furthermore, the method also includes:

[0098] Through the preset interactive interface, the main shape model is demonstrated and the modification information input by the user is obtained;

[0099] Modify the main shape model according to the modification information.

[0100] Furthermore, the scene features include scene simulation features and material types;

[0101] Input the fluid simulation scene and the main body shape model into the preset simulation software to obtain the simulation results of the fluid scene, including:

[0102] The simulation parameters of the fluid simulation scene are configured according to the scene simulation characteristics and the material type, and the configured fluid simulation scene and the main body shape model are simulated and calculated to obtain the simulation result of the fluid scene.

[0103] Further, extracting at least one simulation scene example from a preset physical simulation scene library according to the scene characteristics includes:

[0104] Matching the scene features with the simulation features of each simulation scene example in the preset physical simulation scene library;

[0105] Extract simulation scenario examples that meet preset matching conditions.

[0106] Furthermore, the simulation results are displayed through a preset interactive interface, including:

[0107] The simulation results are displayed in the form of simulation videos on a preset interactive interface.

[0108] The memory 320 may mainly include a program storage area and a data storage area, wherein the program storage area may store an operating system and at least one application required for a function; the data storage area may store data created according to the use of the terminal, etc. In addition, the memory 320 may include a high-speed random access memory, and may also include a non-volatile memory, such as at least one disk storage device, a flash memory device, or other non-volatile solid-state storage device. In some instances, the memory 320 may further include a memory remotely arranged relative to the processor 310, and these remote memories may be connected to the electronic device via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0109] Embodiment 4

[0110] Embodiment 4 of the present application further provides a storage medium containing computer executable instructions, and when the computer executable instructions are executed by a computer processor, they are used to execute a fluid scene generation method, the method comprising:

[0111] When receiving scene description information input by a user, generating a fluid simulation scene and a main body shape model according to the scene description information based on a pre-trained large language model;

[0112] Input the fluid simulation scene and the main body shape model into the preset simulation software to obtain the simulation result of the fluid scene;

[0113] The simulation results are displayed through a preset interactive interface to complete the simulation process of the fluid scene.

[0114] Further, when the scene description information input by the user is received, the fluid simulation scene and the main body shape model are generated according to the scene description information based on the pre-trained large language model, including:

[0115] Inputting the scene description information into the first language model to obtain scene features, and extracting at least one simulation scene example from a preset physical simulation scene library according to the scene features;

[0116] Determine a simulation scene example from at least one simulation scene example as a fluid simulation scene;

[0117] The scene description information is input into the second largest language model to obtain shape generation prompt words, and the main shape model is generated according to the shape generation prompt words.

[0118] Further, determining a simulation scene example from at least one simulation scene example as a fluid simulation scene includes:

[0119] Displaying at least one simulation scenario example as an option and obtaining scenario selection information from a user;

[0120] A simulation scene example is determined from at least one simulation scene example as a fluid simulation scene according to the scene selection information.

[0121] Furthermore, the method also includes:

[0122] Through the preset interactive interface, the main shape model is demonstrated and the modification information input by the user is obtained;

[0123] Modify the main shape model according to the modification information.

[0124] Furthermore, the scene features include scene simulation features and material types;

[0125] Input the fluid simulation scene and the main body shape model into the preset simulation software to obtain the simulation results of the fluid scene, including:

[0126] The simulation parameters of the fluid simulation scene are configured according to the scene simulation characteristics and the material type, and the configured fluid simulation scene and the main body shape model are simulated and calculated to obtain the simulation result of the fluid scene.

[0127] Further, extracting at least one simulation scene example from a preset physical simulation scene library according to the scene characteristics includes:

[0128] Matching the scene features with the simulation features of each simulation scene example in the preset physical simulation scene library;

[0129] Extract simulation scenario examples that meet preset matching conditions.

[0130] Furthermore, the simulation results are displayed through a preset interactive interface, including:

[0131] The simulation results are displayed in the form of simulation videos on a preset interactive interface.

[0132] Of course, the computer executable instructions of a storage medium containing computer executable instructions provided in an embodiment of the present application are not limited to the above method operations, and can also execute related operations in the fluid scene generation method provided in any embodiment of the present application.

[0133] Through the above description of the implementation method, the technicians in the relevant field can clearly understand that the present application can be implemented by means of software and necessary general hardware, and of course it can also be implemented by hardware, but in many cases the former is a better implementation method. Based on such an understanding, the technical solution of the present application can be essentially or the part that contributes to the prior art can be embodied in the form of a software product, and the computer software product can be stored in a computer-readable storage medium, such as a computer floppy disk, read-only memory (ROM), random access memory (RAM), flash memory (FLASH), hard disk or optical disk, etc., including a number of instructions for a computer device (which can be a personal computer, server, or network device, etc.) to execute the methods of each embodiment of the present application.

[0134] It is worth noting that in the embodiment of the above-mentioned search device, the various units and modules included are only divided according to functional logic, but are not limited to the above-mentioned division, as long as the corresponding functions can be achieved; in addition, the specific names of the functional units are only for the convenience of distinguishing each other, and are not used to limit the scope of protection of this application.

[0135] Note that the above are only preferred embodiments of the present application and the technical principles used. Those skilled in the art will understand that the present application is not limited to the specific embodiments herein, and that various obvious changes, readjustments and substitutions can be made by those skilled in the art without departing from the scope of protection of the present application. Therefore, although the present application is described in more detail through the above embodiments, the present application is not limited to the above embodiments, and may include more other equivalent embodiments without departing from the concept of the present application, and the scope of the present application is determined by the scope of the appended claims.

Claims

1. A method for generating a fluid scene, characterized in that: The method comprises: When receiving scene description information input by a user, generating a fluid simulation scene and a main body shape model according to the scene description information based on a pre-trained large language model; Inputting the fluid simulation scene and the main body shape model into a preset simulation software to obtain a simulation result of the fluid scene; The simulation results are displayed through a preset interactive interface to complete the simulation process of the fluid scene.

2. The method according to claim 1, characterized in that The method of generating a fluid simulation scene and a main body shape model according to the scene description information based on a pre-trained large language model when receiving the scene description information input by the user includes: Inputting the scene description information into a first large language model to obtain scene features, and extracting at least one simulation scene example from a preset physical simulation scene library according to the scene features; Determine a simulation scene example from the at least one simulation scene example as a fluid simulation scene; The scene description information is input into the second largest language model to obtain shape generation prompt words, and a main shape model is generated according to the shape generation prompt words.

3. The method according to claim 2, characterized in that The step of determining a simulation scene example from the at least one simulation scene example as a fluid simulation scene comprises: Displaying the at least one simulation scenario example as an option and obtaining scenario selection information from the user; A simulation scene example is determined from the at least one simulation scene example as a fluid simulation scene according to the scene selection information.

4. The method according to claim 2, characterized in that: The method further comprises: Demonstrating the main body shape model through a preset interactive interface and obtaining modification information input by the user; The main body shape model is modified according to the modification information.

5. The method according to claim 2, characterized in that: The scene features include scene simulation features and material types; The step of inputting the fluid simulation scene and the main body shape model into a preset simulation software to obtain a simulation result of the fluid scene comprises: The simulation parameters of the fluid simulation scene are configured according to the scene simulation characteristics and the material type, and the configured fluid simulation scene and the main body shape model are simulated and calculated to obtain the simulation result of the fluid scene.

6. The method according to claim 2, characterized in that The extracting at least one simulation scene example from a preset physical simulation scene library according to the scene feature comprises: Matching the scene features with simulation features of each simulation scene example in the preset physical simulation scene library; Extract simulation scenario examples that meet preset matching conditions.

7. The method according to claim 1, characterized in that The presenting of the simulation results through a preset interactive interface includes: The simulation results are presented in the form of a simulation video on a preset interactive interface.

8. A fluid scene generation device, characterized in that: The device comprises: A generation module, configured to generate a fluid simulation scene and a main body shape model according to the scene description information based on a pre-trained large language model when receiving the scene description information input by the user; A simulation module, used for inputting the fluid simulation scene and the main body shape model into a preset simulation software to obtain a simulation result of the fluid scene; The display module is used to display the simulation results through a preset interactive interface to complete the simulation process of the fluid scene.

9. An electronic device, characterized in that: include: one or more processors; a storage device for storing one or more programs, When the one or more programs are executed by the one or more processors, the one or more processors implement the fluid scene generation method as described in any one of claims 1-7.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the program is executed by a processor, the fluid scene generation method as described in any one of claims 1 to 7 is implemented.

Images