Virtual scene tour path display method and device, computer device and medium

Abstract

The application discloses a virtual scene tour path display method and device, computer equipment and a medium, comprising: collecting current behavior data of a user through a VR device sensor, and analyzing the user's intention according to the current behavior data; dynamically generating a current path in a path planning manner according to the user's intention and virtual scene information; generating a special effect tour path based on the current path, and generating semantic path guidance information in a multi-modal semantic fusion manner. The application realizes intuitive guidance for user navigation, and improves path display intuitiveness and immersion experience.

Description

Methods, devices, computer equipment and media for displaying navigation paths in virtual scenes Technical Field

[0001] This invention relates to the field of virtual reality technology, and in particular to a method, apparatus, computer device, and medium for displaying a virtual scene navigation path. Background Technology

[0002] With the rapid development of Virtual Reality (VR) technology, virtual scenes such as VR museums are gradually becoming more widespread as an important form of cultural dissemination, education, and simulation training. However, existing tour guide technologies have significant shortcomings in path guidance. Traditional tour guides often use arrows, markers, or map navigation. These static designs are difficult to provide an intuitive sense of direction in complex virtual scenes, easily leading users to get lost. Map-based navigation requires frequent switching of perspectives, disrupting immersion and increasing the learning curve. Although some advanced technologies attempt to improve navigation through path projection or dynamic lighting effects, they are still limited to ground-based displays, lacking spatial awareness and interactivity, and failing to meet users' needs for high immersion and intuitive guidance. Summary of the Invention

[0003] This invention provides a method, apparatus, computer device, and storage medium for displaying navigation paths in virtual scenes, so as to improve the intuitiveness and user experience of displaying navigation paths in virtual scenes.

[0004] To address the aforementioned technical problems, embodiments of this application provide a method for displaying a navigation path in a virtual scene, including:

[0005] The VR device's sensors collect the user's current behavioral data, and the user's intent is analyzed based on this data.

[0006] Based on the user intent and virtual scene information, the current path is dynamically generated using path planning.

[0007] Based on the current path, a special effects navigation path is generated, and semantic path guidance information is generated by using multimodal semantic fusion.

[0008] Optionally, generating a special effects navigation path based on the current path includes:

[0009] Generate a flowing starlight effect path based on a generative adversarial network;

[0010] The particle rendering effect is optimized by combining convolutional neural networks with the flowing starlight effect path.

[0011] Optionally, dynamically generating the current path based on the user intent and virtual scene information using path planning includes:

[0012] Determine the target location based on the user's intent;

[0013] Calculate the initial shortest path from the current location to the target location, and dynamically adjust the spacing between path nodes based on user behavior;

[0014] By combining the obstacle radius parameter and path nodes, the initial shortest path is optimized using an addressing algorithm and a deep reinforcement learning algorithm to obtain the current path.

[0015] Optionally, the generation of semantic path guidance information using multimodal semantic fusion includes:

[0016] The target instruction is obtained by parsing the user's voice commands using a multimodal contrastive learning model.

[0017] Based on the target instruction, the user's intent is determined, and the user's semantic information of the image data and the virtual exhibit is encoded and matched to obtain semantic path guidance information.

[0018] Optionally, the step of analyzing user intent based on current behavioral data includes:

[0019] Based on current behavior data, user preference information is determined, wherein the current behavior data includes the gaze direction, current position, movement speed and action, and the user preference information includes the gaze concentration area and gaze duration;

[0020] The user preference information is analyzed using an attention-based sequence model to obtain the user intent.

[0021] To address the aforementioned technical problems, this application also provides a virtual scene navigation path display device, comprising:

[0022] The data acquisition module is used to collect the user's current behavior data through the VR device's sensors and analyze the user's intent based on the current behavior data;

[0023] The path generation module is used to dynamically generate the current path based on the user intent and virtual scene information using a path planning method;

[0024] The navigation guidance module is used to generate special effects navigation paths based on the current path, and to generate semantic path guidance information by using multimodal semantic fusion.

[0025] Optionally, the navigation module includes:

[0026] The special effects generation unit is used to generate flowing starlight special effects paths based on generative adversarial networks.

[0027] The particle rendering unit is used to combine a convolutional neural network to optimize the particle rendering effect of the flowing starlight effect path.

[0028] Optionally, the path generation module includes:

[0029] A target location determination unit is used to determine the target location based on the user's intent;

[0030] The initial path generation unit is used to calculate the initial shortest path from the current location to the target location and dynamically adjust the spacing between path nodes based on user behavior.

[0031] The current path generation unit is used to combine the obstacle radius parameter and the path node, and to optimize the initial shortest path using an addressing algorithm and a deep reinforcement learning algorithm to obtain the current path.

[0032] Optionally, the navigation module further includes:

[0033] The instruction acquisition unit is used to parse user voice instructions through a multimodal contrastive learning model to obtain the target instruction;

[0034] The encoding and matching unit is used to determine the user's intent based on the target instruction, and to encode and match the user's image data and the semantic information of the virtual exhibit to obtain semantic path guidance information.

[0035] Optionally, the data acquisition module includes:

[0036] The preference acquisition unit is used to determine user preference information based on current behavior data, wherein the current behavior data includes the gaze direction, current position, movement speed and action, and the user preference information includes the gaze concentration area and gaze duration.

[0037] The intent analysis unit is used to analyze the user preference information using an attention-based sequence model to obtain the user intent.

[0038] To address the aforementioned technical problems, this application also provides a computer device, including a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, it implements the steps of the aforementioned virtual scene navigation path display method.

[0039] To address the aforementioned technical problems, this application also provides a computer-readable storage medium storing a computer program that, when executed by a processor, implements the steps of the virtual scene navigation path display method described above.

[0040] The virtual scene navigation path display method, apparatus, computer device, and storage medium provided in this invention collect user's current behavior data through VR device sensors and analyze user intent based on the current behavior data; dynamically generate the current path using path planning based on user intent and virtual scene information; generate a special effects navigation path based on the current path; and generate semantic path guidance information using multimodal semantic fusion. This provides intuitive navigation guidance for users, improving the intuitiveness of path display and enhancing the immersive experience. Attached Figure Description

[0041] To more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings used in the description of the embodiments of the present invention will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0042] Figure 1 is an exemplary system architecture diagram in which this application can be applied;

[0043] Figure 2 is a flowchart of an embodiment of the virtual scene navigation path display method of this application;

[0044] Figure 3 is a schematic diagram of the structure of an embodiment of the virtual scene navigation path display device according to this application;

[0045] Figure 4 is a schematic diagram of the structure of an embodiment of a computer device according to this application. Detailed Implementation

[0046] Unless otherwise defined, 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 application pertains; the terminology used herein in the specification of the application is for the purpose of describing particular embodiments only and is not intended to be limiting of the application; the terms "comprising" and "having," and any variations thereof, in the specification, claims, and foregoing drawings of this application, are intended to cover non-exclusive inclusion. The terms "first," "second," etc., in the specification, claims, or foregoing drawings of this application are used to distinguish different objects, not to describe a particular order.

[0047] In this document, the term "embodiment" means that a particular feature, structure, or characteristic described in connection with an embodiment may be included in at least one embodiment of this application. The appearance of this phrase in various places throughout the specification does not necessarily refer to the same embodiment, nor is it a separate or alternative embodiment mutually exclusive with other embodiments. It will be explicitly and implicitly understood by those skilled in the art that the embodiments described herein can be combined with other embodiments.

[0048] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some, not all, of the embodiments of the present invention. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0049] Please refer to Figure 1. As shown in Figure 1, the system architecture 100 may include terminal devices 101, 102, and 103, a network 104, and a server 105. The network 104 is used as a medium to provide a communication link between the terminal devices 101, 102, and 103 and the server 105. The network 104 may include various connection types, such as wired or wireless communication links or fiber optic cables, etc.

[0050] Users can use terminal devices 101, 102, and 103 to interact with server 105 via network 104 to receive or send messages, etc.

[0051] Terminal devices 101, 102, and 103 can be various electronic devices with displays and support web browsing, including but not limited to smartphones, tablets, e-book readers, MP3 players (Moving Picture Experts Group Audio Layer III), MP4 players (Moving Picture Experts Group Audio Layer IV), laptops, and desktop computers, etc.

[0052] Server 105 can be a server that provides various services, such as a backend server that supports the pages displayed on terminal devices 101, 102, and 103.

[0053] It should be noted that the virtual scene navigation path display method provided in this application embodiment is executed by the server, and correspondingly, the virtual scene navigation path display device is set in the server.

[0054] It should be understood that the number of terminal devices, networks, and servers in Figure 1 is merely illustrative. Depending on implementation needs, any number of terminal devices, networks, and servers can be used. The terminal devices 101, 102, and 103 in this embodiment can specifically correspond to application systems in actual production.

[0055] Please refer to Figure 2, which illustrates a method for displaying a virtual scene navigation path according to an embodiment of the present invention. The method is described in detail below, taking its application to the server in Figure 1 as an example:

[0056] S201: Collect the user's current behavior data through VR device sensors, and analyze the user's intent based on the current behavior data.

[0057] Specifically, in terms of hardware, this embodiment relies on VR headsets that support eye tracking and motion capture (such as Oculus Quest 2, HTC Vive, etc.) and computing devices equipped with GPUs (such as NVIDIA RTX 3070 and above graphics cards) to provide the necessary support for path generation and special effects rendering. In the scene modeling stage, a virtual museum environment is constructed using 3D modeling tools (such as Unity or Unreal Engine), and exhibit location information and semantic tags are stored in a database to provide basic data for path planning and generation.

[0058] In one specific optional implementation, analyzing user intent based on current behavioral data includes:

[0059] Based on current behavioral data, determine user preference information. The current behavioral data includes gaze direction, current location, movement speed, and actions. User preference information includes gaze concentration area and gaze duration.

[0060] We employ an attention-based sequence model to analyze user preference information and obtain user intent.

[0061] Specifically, this embodiment utilizes the Transformer model for real-time perception and analysis of user behavior. By monitoring the user's gaze direction, gaze duration, and movement trajectory, the behavior analysis module can perceive the user's interest in specific exhibits and dynamically adjust the display density, brightness, or color of path effects. The parameters analyzed by this module include: gaze duration exceeding 3 seconds is considered an area of ​​interest, and the behavior analysis update frequency is 20 times per second. The multimodal fusion module combines the CLIP model to encode the semantic information of exhibits, user voice commands, and image data, generating a semantically tailored path display that matches the user's needs. When a user queries via voice command (such as "Where are the nearest exhibits?"), the system can match the target exhibit and generate a relevant path in real time. The path's color and shape match the exhibit's theme color, and the path's floating height ranges from 20cm to 150cm, enhancing immersion and sense of direction.

[0062] In this embodiment, the user data collection process includes user entry into the virtual scene, real-time perception of user behavior, and analysis of user behavior data using the Transformer model.

[0063] User enters the virtual scene: This is the beginning of the process, where the user enters the virtual museum environment through VR devices. At this point, the system starts up and prepares to collect user behavior data and interaction information.

[0064] Real-time user behavior monitoring: After a user enters the scene, the system monitors the user's behavior in real time through sensors (such as VR headsets and motion capture devices). This data includes the user's gaze, position, movement speed, and actions (such as head rotation, gestures, etc.).

[0065] Using the Transformer model to analyze user behavior data: The collected user behavior data is transmitted to the Transformer model, which is specifically designed to analyze user interaction patterns and identify user interests. The model determines a user's level of interest in a particular exhibit by analyzing information such as the area where their gaze is focused and the duration of their gaze.

[0066] S202: Based on user intent and virtual scene information, dynamically generate the current path using path planning.

[0067] Specifically, this embodiment combines AI algorithms and deep reinforcement learning (DRL) in path planning, enabling real-time generation and dynamic adjustment of the optimal path. When the user's location, scene layout, or target changes, the deep reinforcement learning model updates the path planning strategy based on real-time feedback, ensuring that the path always points to the optimal target location. This method significantly improves the intelligence level of the navigation system and solves the problem that traditional paths are fixed and cannot adapt to dynamic scenarios.

[0068] It should be noted that the path display design in this embodiment breaks away from the limitations of traditional guide technology, where paths are confined to ground projection. Through 3D path generation technology, flowing, special-effect paths are made to float within the scene (with a height range of 20cm to 150cm). The dynamic adjustment of the path position is combined with the scene content; for example, the path color matches the exhibit's theme color, enhancing the semantic connection between the guide path and the scene. This allows users to perceive a richer sense of spatial hierarchy in an immersive experience. This design effectively improves users' sense of direction and the immersive feeling of virtual reality.

[0069] In one specific optional implementation, dynamically generating the current path using path planning based on user intent and virtual scene information includes:

[0070] Determine the target location based on the user's intent;

[0071] Calculate the initial shortest path from the current location to the target location, and dynamically adjust the spacing between path nodes based on user behavior;

[0072] By combining the obstacle radius parameter and path nodes, the initial shortest path is optimized using addressing algorithms and deep reinforcement learning algorithms to obtain the current path.

[0073] Specifically, path generation employs a combination of AI algorithms and deep reinforcement learning. The AI ​​algorithm calculates the initial shortest path from the user's current location to the target exhibit, with a path node spacing of 1 meter and an obstacle avoidance radius of 50 centimeters. The reinforcement learning model optimizes path planning based on real-time user behavior data to ensure the path's dynamism and intelligence. The model's state space includes the user's position, obstacle positions, and target point position, while the reward function includes the shortest path length, obstacle avoidance (path distance to obstacle ≥ 50 centimeters), and smoothness (path continuity). Path generation parameters include: path calculation latency not exceeding 50 milliseconds, and a path dynamic optimization update frequency of 30 times per second.

[0074] S203: Generate a special effects navigation path based on the current path, and use multimodal semantic fusion to generate semantic path guidance information.

[0075] Specifically, traditional guided tour paths often use static arrows or markers. This embodiment proposes a path display module based on flowing effects. This module consists of a dynamic particle generator, an effects control unit, and a path optimization algorithm. The dynamic particle generator generates flowing starlight particles through a virtual reality engine. The particle diameter ranges from 0.5mm to 1.5mm, the luminosity ranges from 150cd / m² to 300cd / m², and the color dynamically changes between soft cool and warm tones (such as a blue-to-gold gradient) to enhance visual appeal. The effects control unit is responsible for the particle's flow direction, speed (controlled within the range of 0.5m / s to 1.5m / s), and trajectory shape, ensuring it always flows along the guided tour path and adjusting the flow angle according to the user's perspective to ensure clear directionality.

[0076] Furthermore, the deep integration of 3D spatial paths with virtual scenes is achieved. Utilizing 3D path construction technology, flowing starlight effect paths are suspended between 20cm and 150cm above the ground. The path's position and shape can be flexibly adjusted according to the user's location and exhibition content, supporting navigation needs for straight lines, curves, forks, and multi-level spaces.

[0077] In one specific optional implementation, generating a special effects navigation path based on the current path includes:

[0078] Generate a flowing starlight effect path based on a generative adversarial network;

[0079] By incorporating convolutional neural networks, the particle rendering effect of the flowing starlight effect path is optimized.

[0080] Specifically, the dynamic visual effects of the navigation path are generated using a Generative Adversarial Network (GAN). The generator in the GAN is responsible for creating high-quality starlight particle flow effects, including particle shapes (such as dots, lines, ripples, etc.), flow trajectories, color gradients, and brightness adjustments. The discriminator then evaluates whether the generated effects meet visual requirements. By continuously optimizing the generator's output, a highly realistic, dynamic, and scene-integrated flow path display effect is achieved. The particle shape, color, brightness, and flow speed can be dynamically adjusted (e.g., particle size from 0.5mm to 1.5mm, brightness range from 150cd / m² to 300cd / m², and flow speed from 0.5m / s to 1.5m / s), giving the path extremely high visual appeal and dynamic expressiveness. This design not only solves the problems of monotonous traditional static path markings and poor information display intuitiveness but also enhances the path's dynamism and sense of direction through flow effects, providing users with clearer and more intuitive guidance in complex 3D scenes.

[0081] In one specific optional implementation, the semantic path guidance information generated by employing multimodal semantic fusion includes:

[0082] The target instruction is obtained by parsing the user's voice commands using a multimodal contrastive learning model.

[0083] Based on the target instructions, the user's intent is determined, and the semantic information of the user's image data and virtual exhibits is encoded and matched to obtain semantic path guidance information.

[0084] Specifically, this embodiment utilizes multimodal data fusion and intelligent navigation. Based on a multimodal AI model (such as CLIP), it achieves a deep integration of navigation paths and scene semantics, comprehensively analyzing scene images, text information, and user voice commands to generate paths. For example, when a user inquires about a specific exhibit or theme via voice, the system can match the target exhibit through semantic understanding and dynamically generate a path to guide the user to the corresponding location. This function breaks through the limitations of traditional navigation technology in scene information association, providing a new solution for intelligent and semantic navigation. Multimodal semantic fusion path planning and special effects display. A multimodal AI model (such as CLIP) is used for semantic information processing and fusion. The system uses multimodal data such as speech recognition, visual understanding, and text analysis, combined with the user's voice commands and visual points of interest, to generate navigation paths that match the user's needs in real time. This multimodal semantic fusion technology can not only understand the user's verbal commands but also generate dynamic paths related to the target exhibits based on the user's gaze behavior, ensuring the semantic relevance and accuracy of the path guidance. By jointly training on multiple data types, the system can more accurately understand and respond to user intentions, enhancing the intelligence and naturalness of the tour guiding process.

[0085] Furthermore, this embodiment generates a path that meets the user's needs based on the voice information parsed by the CLIP model and the semantic data of the exhibits. The path is not only based on the user's current location, but also takes into account the semantic attributes of the exhibits, ensuring that the path is related to the theme of the exhibits and improving the intelligence and accuracy of the guided tour.

[0086] Furthermore, in this embodiment, the system continuously monitors changes in user behavior and detects in real time whether the tour route needs to be adjusted. If the user's behavior changes (e.g., lingering in a certain area for an extended period or changing the direction of their gaze), the system will adjust the route and effects based on the new data feedback to ensure a smooth and personalized tour experience.

[0087] In this embodiment, the user's current behavior data is collected through VR device sensors, and the user's intent is analyzed based on the current behavior data. Based on the user's intent and virtual scene information, a current path is dynamically generated using path planning. A special effects-based guided route is generated based on the current path, and semantic path guidance information is generated using multimodal semantic fusion. This provides intuitive navigation guidance for the user, improving the intuitiveness of the path display and the immersive experience.

[0088] It should be understood that the sequence number of each step in the above embodiments does not imply the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present invention.

[0089] Figure 3 shows a schematic block diagram of a virtual scene navigation path display device that corresponds one-to-one with the virtual scene navigation path display method described in the above embodiments. As shown in Figure 3, the virtual scene navigation path display device includes a data acquisition module 31, a path generation module 32, and a navigation guidance module 33. Detailed descriptions of each functional module are as follows:

[0090] The data acquisition module 31 is used to collect the user's current behavior data through the VR device's sensors and analyze the user's intent based on the current behavior data;

[0091] The path generation module 32 is used to dynamically generate the current path based on the user intent and virtual scene information using a path planning method;

[0092] The navigation guidance module 33 is used to generate a special effects navigation path based on the current path, and to generate semantic path guidance information by using a multimodal semantic fusion method.

[0093] Optionally, the navigation module 33 includes:

[0094] The special effects generation unit is used to generate flowing starlight special effects paths based on generative adversarial networks.

[0095] The particle rendering unit is used to combine a convolutional neural network to optimize the particle rendering effect of the flowing starlight effect path.

[0096] Optionally, the path generation module 32 includes:

[0097] A target location determination unit is used to determine the target location based on the user's intent;

[0098] The initial path generation unit is used to calculate the initial shortest path from the current location to the target location and dynamically adjust the spacing between path nodes based on user behavior.

[0099] The current path generation unit is used to combine the obstacle radius parameter and the path node, and to optimize the initial shortest path using an addressing algorithm and a deep reinforcement learning algorithm to obtain the current path.

[0100] Optionally, the navigation module 33 further includes:

[0101] The instruction acquisition unit is used to parse user voice instructions through a multimodal contrastive learning model to obtain the target instruction;

[0102] The encoding and matching unit is used to determine the user's intent based on the target instruction, and to encode and match the user's image data and the semantic information of the virtual exhibit to obtain semantic path guidance information.

[0103] Optionally, the data acquisition module 31 includes:

[0104] The preference acquisition unit is used to determine user preference information based on current behavior data, wherein the current behavior data includes the gaze direction, current position, movement speed and action, and the user preference information includes the gaze concentration area and gaze duration.

[0105] The intent analysis unit is used to analyze the user preference information using an attention-based sequence model to obtain the user intent.

[0106] Specific limitations regarding the virtual scene navigation path display device can be found in the limitations of the virtual scene navigation path display method described above, and will not be repeated here. Each module in the aforementioned virtual scene navigation path display device can be implemented entirely or partially through software, hardware, or a combination thereof. These modules can be embedded in or independent of the processor in the computer device in hardware form, or stored in the memory of the computer device in software form, so that the processor can call and execute the operations corresponding to each module.

[0107] To address the aforementioned technical problems, this application also provides a computer device. Please refer to Figure 4 for details; Figure 4 is a basic structural block diagram of the computer device according to this embodiment.

[0108] The computer device 4 includes a memory 41, a processor 42, and a network interface 43 that are interconnected via a system bus. It should be noted that only the computer device 4 with components connected to the memory 41, processor 42, and network interface 43 is shown in the figure; however, it should be understood that it is not required to implement all the components shown, and more or fewer components can be implemented alternatively. Those skilled in the art will understand that the computer device described here is a device capable of automatically performing numerical calculations and / or information processing according to pre-set or stored instructions, and its hardware includes, but is not limited to, microprocessors, application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), digital signal processors (DSPs), embedded devices, etc.

[0109] The computer device can be a desktop computer, laptop, handheld computer, or cloud server, etc. The computer device can interact with the user via a keyboard, mouse, remote control, touchpad, or voice control.

[0110] The memory 41 includes at least one type of readable storage medium, including flash memory, hard disk, multimedia card, card-type memory (e.g., SD or D-interface display memory), random access memory (RAM), static random access memory (SRAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), programmable read-only memory (PROM), magnetic memory, disk, optical disk, etc. In some embodiments, the memory 41 may be an internal storage unit of the computer device 4, such as the hard disk or memory of the computer device 4. In other embodiments, the memory 41 may also be an external storage device of the computer device 4, such as a plug-in hard disk, smart media card (SMC), secure digital (SD) card, flash card, etc., equipped on the computer device 4. Of course, the memory 41 may include both the internal storage unit and its external storage device of the computer device 4. In this embodiment, the memory 41 is typically used to store the operating system and various application software installed on the computer device 4, such as the program code for a virtual scene navigation path display method. In addition, the memory 41 can also be used to temporarily store various types of data that have been output or will be output.

[0111] In some embodiments, the processor 42 may be a central processing unit (CPU), a controller, a microcontroller, a microprocessor, or other data processing chip. The processor 42 is typically used to control the overall operation of the computer device 4. In this embodiment, the processor 42 is used to run program code stored in the memory 41 or process data, for example, to run program code for a virtual scene navigation path display method.

[0112] The network interface 43 may include a wireless network interface or a wired network interface, which is typically used to establish communication connections between the computer device 4 and other electronic devices.

[0113] This application also provides another embodiment, namely, a computer-readable storage medium storing an interface display program, which can be executed by at least one processor to cause the at least one processor to perform the steps of the virtual scene navigation path display method described above.

[0114] Through the above description of the embodiments, those skilled in the art can clearly understand that the methods of the above embodiments can be implemented by means of software plus necessary general-purpose hardware platforms. Of course, they can also be implemented by hardware, but in many cases the former is a better implementation method. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product is stored in a storage medium (such as ROM / RAM, magnetic disk, optical disk) and includes several instructions to cause a terminal device (which may be a mobile phone, computer, server, air conditioner, or network device, etc.) to execute the methods described in the various embodiments of this application.

[0115] Obviously, the embodiments described above are only some embodiments of this application, not all embodiments. The accompanying drawings show preferred embodiments of this application, but do not limit the patent scope of this application. This application can be implemented in many different forms; rather, these embodiments are provided to provide a more thorough and comprehensive understanding of the disclosure of this application. Although this application has been described in detail with reference to the foregoing embodiments, those skilled in the art can still modify the technical solutions described in the foregoing specific embodiments, or make equivalent substitutions for some of the technical features. Any equivalent structures made using the content of this application's specification and drawings, directly or indirectly applied to other related technical fields, are similarly within the scope of patent protection of this application.

Claims

1. A method for displaying a navigation path in a virtual scene, characterized in that, include: The VR device's sensors collect the user's current behavior data, and an attention-based sequence model is used to analyze the user's intent based on the current behavior data. Based on the user intent and virtual scene information, the current path is dynamically generated using path planning. A special effects-based guided tour path is generated based on the current path. A multimodal contrastive learning model is used to parse user voice commands to obtain target commands. Based on the target commands, the user intent is determined, and the user intent is encoded and matched with image data and semantic information of virtual exhibits to generate semantically meaningful path guidance information. The image data corresponds to scene images. The generation of the special effects-based guided tour path based on the current path includes: generating a flowing starlight effect path based on a generative adversarial network; and optimizing particle rendering effects of the flowing starlight effect path using a convolutional neural network. The dynamic generation of the current path based on the user intent and virtual scene information using path planning includes: determining the target location based on the user intent. The process involves: setting the initial shortest path from the current location to the target location and dynamically adjusting the spacing between path nodes based on user behavior; optimizing the initial shortest path using an addressing algorithm and a deep reinforcement learning algorithm, combining the obstacle avoidance radius parameter and path nodes to obtain the current path; the obstacle avoidance radius parameter representing the distance between the path and obstacles; and analyzing user intent based on current behavior data, including determining user preference information based on current behavior data (such as gaze direction, current location, movement speed, and actions), and user preference information (such as gaze concentration area and gaze duration); and using an attention-based sequence model to analyze the user preference information to obtain user intent.

2. A virtual scene navigation path display device, characterized in that, The virtual scene navigation path display method according to claim 1, the device includes: a data acquisition module, used to collect the user's current behavior data through VR device sensors, and analyze the user's intent based on the current behavior data; a path generation module, used to dynamically generate the current path according to the user's intent and virtual scene information using a path planning method; and a navigation guidance module, used to generate a special effects navigation path based on the current path, and generate semantic path guidance information using a multimodal semantic fusion method.

3. The virtual scene navigation path display device as described in claim 2, characterized in that, The navigation guidance module further includes: an instruction acquisition unit, used to parse user voice instructions through a multimodal contrastive learning model to obtain target instructions; and an encoding matching unit, used to determine user intent based on the target instructions, and to encode and match the user intent with image data and semantic information of virtual exhibits to obtain semantic path guidance information.

4. The virtual scene navigation path display device as described in claim 2, characterized in that, The data acquisition module includes: a preference acquisition unit, used to determine user preference information based on current behavior data, wherein the current behavior data includes gaze direction, current position, movement speed and action, and the user preference information includes gaze concentration area and gaze duration; and an intent analysis unit, used to analyze the user preference information using a sequence model based on an attention mechanism to obtain user intent.

5. A computer 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 computer program, it implements the virtual scene navigation path display method as described in claim 1.

6. A computer-readable storage medium storing a computer program, characterized in that, When the computer program is executed by the processor, it implements the virtual scene navigation path display method as described in claim 1.

Images