Tree pruning visualization method and device, equipment, storage medium and computer program product

Abstract

The invention relates to the technical field of computers, in particular to a tree pruning visualization method and device, equipment, a storage medium and a computer program product. The method comprises the following steps: determining three-dimensional structure information of a to-be-processed tree according to a multi-angle image and environmental data of the to-be-processed tree; generating an initial tree model for virtual pruning based on the three-dimensional structure information; inputting the three-dimensional structure information into a preset multi-modal pruning inference model to obtain a pruning strategy; based on the pruning strategy, the AR technology is adopted to perform virtual pruning on the initial tree model, and the pruned target tree model is displayed in real time, so that the tree pruning efficiency is improved.

Description

Technical Field

[0001] The present application relates to the field of computer technology, and particularly to a method, device, equipment, storage medium and computer program product for visualizing tree pruning. Background Art

[0002] Tree pruning is an important horticultural and forestry management practice, aiming to promote the healthy growth of trees, optimize their structure, and meet specific aesthetic or functional requirements by selectively removing certain parts of the trees (such as branches, buds or roots). The correct tree pruning method can not only improve the beauty and health of trees, but also extend their lifespan and reduce potential safety hazards. However, the traditional tree pruning process usually relies on manual experience and has high requirements for the professional knowledge level of operators, resulting in poor pruning efficiency. Therefore, how to improve the tree pruning efficiency has become an urgent technical problem to be solved. Summary of the Invention

[0003] The main purpose of the present application is to provide a method, device, equipment, storage medium and computer program product for visualizing tree pruning, aiming to solve the technical problem of how to improve the tree pruning efficiency.

[0004] To achieve the above purpose, the present application provides a method for visualizing tree pruning, and the method includes the following steps:

[0005] Determine the three-dimensional structure information of the tree to be processed according to the multi-angle images and environmental data of the tree to be processed;

[0006] Generate an initial tree model for virtual pruning based on the three-dimensional structure information;

[0007] Input the three-dimensional structure information into a preset multi-modal pruning inference model to obtain a pruning strategy;

[0008] Based on the pruning strategy, use AR technology to perform virtual pruning on the initial tree model and display the pruned target tree model in real time.

[0009] In an embodiment, the step of determining the three-dimensional structure information of the tree to be processed according to the multi-angle images and environmental data of the tree to be processed includes:

[0010] Obtain the multi-angle images and environmental data of the tree to be processed, and the environmental data includes geographical location information, temperature information, humidity information and sunlight information;

[0011] Preprocess the multi-angle images to obtain preprocessed images, and the preprocessing includes one or more of denoising, alignment and image segmentation;

[0012] Extract key feature points of the preprocessed image based on a preset deep learning algorithm;

[0013] Determine the three-dimensional structure information of the tree to be processed according to the key feature points and the environmental data.

[0014] In one embodiment, the step of generating an initial tree model for virtual pruning based on the three-dimensional structure information includes:

[0015] Perform geometric optimization processing on the three-dimensional structure information to obtain optimized structure information, and the geometric optimization processing includes one or more of redundant point cloud elimination, error reconstruction, and missing area filling;

[0016] Generate an initial three-dimensional model based on the optimized structure information;

[0017] Perform semantic segmentation processing on the initial three-dimensional model, and reorganize the initial three-dimensional model according to the semantic segmentation result to obtain the initial tree model for virtual pruning.

[0018] In one embodiment, after the step of generating an initial tree model for virtual pruning based on the three-dimensional structure information, it further includes:

[0019] Perform smoothing processing on the initial tree model;

[0020] Adjust the visual effect of the smoothed initial tree model based on the sunlight information;

[0021] Perform rendering and visualization processing on the adjusted initial tree model based on a preset rendering engine.

[0022] In one embodiment, the step of virtually pruning the initial tree model using AR technology based on the pruning strategy and real-time displaying the pruned target tree model includes:

[0023] Parse the pruning strategy to determine the recommended pruning position, recommended cutting angle, and recommended pruning time;

[0024] When a pruning confirmation instruction is obtained, virtually prune the initial tree model using AR technology based on the recommended pruning position, the recommended cutting angle, and the recommended pruning time;

[0025] Render the initially tree model after virtual pruning using a preset dynamic rendering algorithm to obtain a target tree model, and real-time display the pruned target tree model.

[0026] In one embodiment, after the step of virtually pruning the initial tree model using AR technology based on the pruning strategy and displaying the target tree model after pruning in real time, the method further includes:

[0027] When a pruning modification instruction is received, based on the pruning modification instruction, adjust the recommended pruning position, the recommended cutting angle, and the recommended pruning time;

[0028] Based on the adjusted recommended pruning position, the recommended cutting angle, and the recommended pruning time, use AR technology to virtually prune the initial tree model and display the initial tree model after pruning;

[0029] Obtain interactive evaluation data, and optimize the preset multimodal pruning inference model based on the interactive evaluation data.

[0030] In addition, to achieve the above object, the present application also proposes a tree pruning visualization device, where the tree pruning visualization device includes:

[0031] A structure determination module, configured to determine three-dimensional structure information of the tree to be processed according to multi-angle images and environmental data of the tree to be processed;

[0032] A model generation module, configured to generate an initial tree model for virtual pruning based on the three-dimensional structure information;

[0033] A strategy generation module, configured to input the three-dimensional structure information into a preset multimodal pruning inference model to obtain a pruning strategy;

[0034] A target module, configured to virtually prune the initial tree model using AR technology based on the pruning strategy and display the target tree model after pruning in real time.

[0035] In addition, to achieve the above object, the present application also proposes a tree pruning visualization device, where the device includes: a memory, a processor, and a tree pruning visualization program stored on the memory and executable on the processor, and the tree pruning visualization program is configured to implement the steps of the tree pruning visualization method as described above.

[0036] In addition, to achieve the above object, the present application also proposes a storage medium, where a tree pruning visualization program is stored on the storage medium, and when the tree pruning visualization program is executed by a processor, it implements the steps of the tree pruning visualization method as described above.

[0037] In addition, to achieve the above object, the present application also proposes a computer program product, which includes a computer program. When the computer program is executed by a processor, it implements the steps of the tree pruning visualization method described above.

[0038] The present application determines the three-dimensional structure information of the tree to be processed based on multi-angle images and environmental data of the tree to be processed; generates an initial tree model for virtual pruning based on the three-dimensional structure information; inputs the three-dimensional structure information into a preset multi-modal pruning inference model to obtain a pruning strategy; based on the pruning strategy, uses AR technology to perform virtual pruning on the initial tree model and displays the pruned target tree model in real time. The present application determines the three-dimensional structure information through multi-angle images and environmental data of the tree to be processed, and generates an initial tree model for virtual pruning, ensuring the integrity and accuracy of the data basis for pruning operations; inputs the three-dimensional structure information into a preset multi-modal pruning inference model to generate a pruning strategy to clarify the specific position and method of pruning; based on the pruning strategy, uses AR technology to perform virtual pruning on the initial tree model and displays the pruned target tree model in real time, enabling users to intuitively understand the pruning effect and improving the efficiency of tree pruning. Description of the Drawings

[0039] Figure 1 It is a schematic flowchart of the first embodiment of the tree pruning visualization method of the present application;

[0040] Figure 2 It is a schematic sub-flowchart of the second embodiment of the tree pruning visualization method of the present application;

[0041] Figure 3 It is a schematic sub-flowchart of the third embodiment of the tree pruning visualization method of the present application;

[0042] Figure 4 It is a schematic module structure diagram of the tree pruning visualization device in the embodiment of the present application;

[0043] Figure 5 It is a schematic device structure diagram of the hardware operating environment involved in the tree pruning visualization method in the embodiment of the present application.

[0044] The implementation, functional features and advantages of the object of the present application will be further described with reference to the embodiments and the accompanying drawings. Detailed Embodiments

[0045] It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0046] To better understand the technical solution of the present application, the following will be described in detail in conjunction with the accompanying drawings of the specification and specific embodiments.

[0047] It should be noted that tree pruning is an important horticultural and forestry management practice. It aims to promote the healthy growth of trees, optimize their structure, and meet specific aesthetic or functional requirements by selectively removing certain parts of the trees (such as branches, buds, or roots). The correct tree pruning method can not only enhance the beauty and health of the trees, but also extend their lifespan and reduce potential safety hazards. However, the traditional tree pruning process usually relies on manual experience and has high requirements for the professional knowledge level of the operator, resulting in poor pruning efficiency. Therefore, how to improve the tree pruning efficiency has become a technical problem to be solved urgently.

[0048] The main solution of this application is: determine the three-dimensional structure information of the tree to be processed according to the multi-angle images and environmental data of the tree to be processed; generate an initial tree model for virtual pruning based on the three-dimensional structure information; input the three-dimensional structure information into a preset multi-modal pruning inference model to obtain a pruning strategy; based on the pruning strategy, use AR technology to perform virtual pruning on the initial tree model and display the pruned target tree model in real time.

[0049] This application determines the three-dimensional structure information through the multi-angle images and environmental data of the tree to be processed, and generates an initial tree model for virtual pruning, ensuring that the data basis for pruning operations is complete and accurate; inputs the three-dimensional structure information into a preset multi-modal pruning inference model to generate a pruning strategy to clarify the specific positions and methods of pruning; based on the pruning strategy, uses AR technology to perform virtual pruning on the initial tree model and displays the pruned target tree model in real time, enabling users to intuitively understand the pruning effect and improving the efficiency of tree pruning.

[0050] It should be noted that the execution subject of the method in this embodiment can be a computing service device with data processing, network communication, and program running functions, or the above-mentioned tree pruning visualization device with the same or similar functions. This embodiment and the following embodiments will be described by taking the tree pruning visualization device as an example.

[0051] Based on this, the first embodiment of the tree pruning visualization method of this application is proposed. Please refer to Figure 1 , Figure 1 which is the flowchart of the first embodiment of the tree pruning visualization method of this application.

[0052] In this embodiment, the method includes the following steps:

[0053] S1: Determine the three-dimensional structure information of the tree to be processed according to the multi-angle images and environmental data of the tree to be processed;

[0054] It should be noted that multi - angle images refer to images of trees taken from different perspectives, usually collected by the high - resolution camera of a mobile terminal (such as a smartphone), with the aim of obtaining complete visual information of various parts of the tree. Environmental data refers to external environmental information related to the growth of the tree, including but not limited to geographical location information, temperature, humidity, and sunlight intensity. These data are used to assist in analyzing the growth status of the tree and environmental impacts. The three - dimensional structure information is a three - dimensional geometric model generated by calculating multi - angle images and environmental data, which can reflect the true form of the tree in three - dimensional space, including the trunk, branches, and their relative positions, etc.

[0055] Specifically, use the high - resolution camera of the mobile terminal to take pictures of the tree to be processed from multiple angles, obtaining multiple images covering its overall structure. At the same time, collect parameters related to the tree environment, such as geographical location information (obtained through the GPS module), temperature and humidity (through built - in sensors), and sunlight direction, etc. These data provide multi - modal input information for subsequent modeling.

[0056] Furthermore, process the collected multi - angle images, including denoising, image alignment, and segmentation to extract key feature points. Subsequently, through three - dimensional reconstruction algorithms (such as multi - view geometry algorithms or deep - learning models), combined with environmental data to calibrate the scale and position of the model, generating complete three - dimensional structure information. The final three - dimensional model can not only reflect the overall shape of the tree but also label the structural features of different parts, such as the hierarchical relationship between the main trunk and branches.

[0057] By integrating multi - angle images and environmental data, comprehensively collect the geometric and environmental feature information of the tree, ensuring the accuracy and integrity of the three - dimensional structure information. Precise three - dimensional structure information lays the foundation for the generation of subsequent virtual pruning models, helping the inference model to formulate pruning strategies more scientifically. The introduction of environmental data makes three - dimensional modeling not only focus on the shape of the tree itself but also consider the impact of the external environment on its structure, such as sunlight direction and humidity conditions, thereby improving the practical applicability of the model. Traditional manual assessment of tree structure requires professional knowledge, while this step significantly reduces the complexity of operation through an automated modeling process, enabling ordinary users to easily participate.

[0058] S2: Generate an initial tree model for virtual pruning based on the three - dimensional structure information;

[0059] It should be noted that virtual pruning refers to simulating the tree pruning process through computer technology. Users can operate and observe the tree model in a virtual environment to understand the pruning effect in advance. The initial tree model is a virtual three - dimensional model constructed based on the three - dimensional structure information, used to present the original state of the tree and provide a data basis for subsequent pruning simulation and strategy generation.

[0060] Specifically, based on the generated three-dimensional structure information, the data is geometrically optimized. This specifically includes removing redundant point cloud data, correcting possible errors in 3D reconstruction, and supplementing missing areas. The optimized three-dimensional structure information ensures the integrity and high precision of the model, providing more reliable data support for subsequent operations.

[0061] Furthermore, an initial three-dimensional tree model is generated using the optimized three-dimensional structure information, and semantic segmentation is performed on the model to label different components of the tree (such as the trunk, main branches, side branches, and leaves) as different categories. Based on the semantic segmentation results, the model is hierarchically reorganized to generate a hierarchical initial tree model. Finally, through the rendering engine, the model is transformed into a virtual pruning object for user visualization operations, supporting interaction and adjustment.

[0062] Through geometric optimization and semantic segmentation, the generated initial tree model can accurately reflect the true structure of the tree, ensuring the reliability of pruning recommendations. Through hierarchical reorganization, the initial tree model supports users to operate on specific branches, improving the flexibility and convenience of pruning simulation. The virtual pruning model allows users to preview the pruning effect in a virtual environment, avoiding errors and damages that may be caused by directly pruning real trees. The initial model provides accurate basic data for the multi-modal pruning inference model, making the generated pruning strategy more scientific and personalized to meet different environmental and user needs. The high-quality initial model combined with the visualization effect provides an intuitive interaction experience for users, enabling even non-professional users to easily get started.

[0063] S3: Input the three-dimensional structure information into a preset multi-modal pruning inference model to obtain a pruning strategy;

[0064] It should be noted that the preset multi-modal pruning inference model refers to a model trained through deep learning or other artificial intelligence technologies, which can comprehensively process multi-modal data (such as images, environmental data, three-dimensional structure information, etc.) and generate personalized pruning strategies based on the input data. This model has usually been pre-trained and has a certain degree of generality and pertinence. The pruning strategy is a targeted pruning recommendation output by the inference model, including information such as the position of the branches to be pruned, the recommended cutting angle, and the pruning time, aiming to optimize the health, growth, and aesthetics of the tree.

[0065] Specifically, the three-dimensional structure information is used as the main input, and at the same time, environmental data (such as geographical location, climate conditions, etc.) is combined and input into the preset multi-modal pruning inference model. The model first analyzes the input data through a feature extraction module to extract key feature information of the tree, such as the branch structure, the position of the main trunk, the density of branch distribution, and the health status of the tree. At the same time, the environmental data provides external influencing factors, such as the best pruning season, the impact of humidity on pruning, etc., providing auxiliary support for strategy generation.

[0066] Furthermore, based on the extracted feature information, the inference model uses multimodal fusion technology to combine geometric structure data with environmental feature data and performs inference calculations through a trained deep learning framework. During the inference process, the model comprehensively considers the growth requirements of the trees (such as promoting health or shaping aesthetics) and user preferences to generate specific pruning strategies, including the recommended positions of the branches to be pruned, cutting angles, and optimal pruning times, etc. The finally output pruning strategy will be transmitted to the subsequent visualization and virtual pruning modules in the form of structured data.

[0067] By inputting three-dimensional structure information and environmental data, the model can generate highly accurate and scientific pruning strategies, avoiding the inaccuracies caused by insufficient experience in manual pruning. The multimodal inference model can fuse geometric information and environmental data to provide more personalized and scenario-based pruning suggestions. For example, it optimizes the pruning time and angle according to humidity and sunlight direction to improve the pruning effect. Using the preset model to automatically generate pruning strategies greatly reduces the workload of users analyzing the tree shape and environmental conditions, enabling non-professional users to also obtain high-quality pruning guidance. The model can generate personalized strategies for different tree species, environmental conditions, and user goals (such as health, aesthetic appearance, or functional requirements) to meet the pruning needs of different scenarios. The pruning strategy provides clear and structured specific operation guidelines, laying the foundation for virtual pruning and real-time effect display, and enhancing the user experience and pruning efficiency.

[0068] S4: Based on the pruning strategy, use AR technology to perform virtual pruning on the initial tree model and display the pruned target tree model in real time.

[0069] It should be noted that AR technology refers to Augmented Reality technology. By overlaying virtual information on the user's real view, it provides a real-time interactive and visual operation experience. The target tree model refers to the three-dimensional model generated after virtual pruning, reflecting the shape of the pruned tree and facilitating the user to intuitively understand the pruning effect.

[0070] Specifically, apply the pruning strategy to the initial tree model and analyze the recommended pruning positions and cutting angles. Use AR technology to highlight the branches to be pruned on the user device screen in the form of virtual markers, and clarify the cutting positions and angles through virtual lines or marker points. The user can view the pruning suggestions on the screen in real time and adjust the pruning plan through gestures or touches, such as selecting specific branches or optimizing the cutting angle.

[0071] Furthermore, after the user confirms the pruning operation, the system virtually prunes the initial tree model according to the pruning strategy and the user's adjustment instructions. During the pruning process, the branches to be pruned are dynamically removed, and the three-dimensional structure of the tree is updated in real time to generate the target tree model after pruning. Through AR technology, the user can visually see the shape of the model after pruning on the screen and switch perspectives or zoom in and out to observe the pruning effect. In addition, the target tree model supports the comparison display before and after pruning to help the user intuitively evaluate the pruning effect.

[0072] By using AR technology to real-time annotate pruning suggestions and dynamically display the target tree model after pruning, the user can intuitively understand the pruning effect, greatly reducing the complexity of the operation. The user can adjust the pruning plan through touch or gestures, explore different pruning strategies and effects in the virtual environment, improving the flexibility and accuracy of the operation. Virtual pruning avoids the irreversible losses that may be caused by directly operating on real trees. The user can test the pruning effect multiple times in the simulation and select the best plan. The target tree model after pruning can be displayed immediately, allowing the user to quickly obtain feedback during the operation and adjust the pruning plan according to needs, improving the operation efficiency. The provided virtual pruning and visualization guidance significantly reduce the technical threshold of pruning, enabling non-professional users to efficiently complete high-quality tree pruning tasks. The comparison display of the model before and after pruning helps the user clearly understand the impact of pruning on the tree shape, providing a scientific basis for decision-making.

[0073] In this embodiment, the three-dimensional structure information of the tree to be processed is determined based on the multi-angle images and environmental data of the tree to be processed; based on the three-dimensional structure information, an initial tree model for virtual pruning is generated; the three-dimensional structure information is input into a preset multi-modal pruning inference model to obtain a pruning strategy; based on the pruning strategy, the initial tree model is virtually pruned using AR technology, and the target tree model after pruning is displayed in real time. In this embodiment, the three-dimensional structure information is determined through the multi-angle images and environmental data of the tree to be processed, and an initial tree model for virtual pruning is generated to ensure the integrity and accuracy of the data basis for the pruning operation; the three-dimensional structure information is input into a preset multi-modal pruning inference model to generate a pruning strategy to clarify the specific position and method of pruning; based on the pruning strategy, the initial tree model is virtually pruned using AR technology, and the target tree model after pruning is displayed in real time, enabling the user to intuitively understand the pruning effect and improving the efficiency of tree pruning.

[0074] Based on the above first embodiment, a second embodiment of the tree pruning visualization method of the present application is proposed. Please refer to Figure 2 , Figure 2 which is a schematic diagram of a sub-process in the second embodiment of the tree pruning visualization method of the present application.

[0075] As Figure 2 shown, in this embodiment, step S1 includes:

[0076] S11: Obtain multi - angle images and environmental data of the tree to be processed, where the environmental data includes geographical location information, temperature information, humidity information, and sunlight information;

[0077] S12: Pre - process the multi - angle images to obtain pre - processed images, where the pre - processing includes one or more of denoising, alignment, and image segmentation;

[0078] S13: Extract key feature points of the pre - processed images based on a preset deep - learning algorithm;

[0079] S14: Determine the three - dimensional structure information of the tree to be processed according to the key feature points and the environmental data.

[0080] It should be noted that environmental data refers to external information related to the tree growth environment, including geographical location information (such as the specific location of the tree), temperature, humidity, and sunlight, etc. These information provide environmental background support for three - dimensional modeling. The pre - processed image is optimized image data obtained by processing the collected original images through denoising, alignment, segmentation, etc., and is used to extract key features. Key feature points refer to significant structural points extracted from the image, such as the connection points between the trunk and branches, the bifurcation points of branches, etc. These feature points are the basis for three - dimensional reconstruction.

[0081] Specifically, use the high - resolution camera of the mobile terminal to take pictures of the tree to be processed from different angles to obtain multi - angle images covering the overall shape of the tree. At the same time, collect environmental data through built - in sensors of the device (such as GPS, temperature - humidity sensors), including the geographical location information of the tree, the current temperature, humidity, and sunlight direction, etc. The collected multi - angle images are first subjected to pre - processing operations, including: Denoising: Eliminate the noise introduced during the shooting process due to lighting conditions, device jitter, etc.; Alignment: Correct the shooting angles of the images to ensure consistency between the images; Image segmentation: Separate the background and the main body of the tree to highlight the structural features of the tree.

[0082] Furthermore, apply a deep - learning algorithm (such as a convolutional neural network) to the pre - processed image data for feature point extraction. This process identifies and marks the key positions in the image, such as the bifurcation points of the trunk, main branches, and lateral branches. Combine environmental data (such as sunlight direction and humidity information) to calibrate the feature points to improve the spatial accuracy of the feature points. Finally, through the multi - view geometric reconstruction method, integrate these feature points into three - dimensional structure information to generate a three - dimensional model of the tree at real scale, which completely reflects the shape and spatial distribution of the tree.

[0083] Through the combination of multi-angle images and environmental data, the three-dimensional structural information can comprehensively and accurately reflect the morphology of trees, providing a reliable basis for subsequent pruning. Image preprocessing operations (such as denoising and alignment) improve the data quality, ensuring that the extracted feature points are accurate and consistent. Environmental data (such as sunlight and humidity) enable the generated three-dimensional model to not only reflect the spatial morphology of trees but also adapt to the specific growth environment requirements. The three-dimensional structural information lays a scientific foundation for the generation of subsequent pruning strategies, making pruning decisions more precise. The automated image processing and modeling process reduces the requirements for users' professional knowledge and improves the ease of use and efficiency of operations.

[0084] Based on the first embodiment described above, in this embodiment, step S2 includes:

[0085] S21: Perform geometric optimization processing on the three-dimensional structural information to obtain optimized structural information. The geometric optimization processing includes one or more of redundant point cloud elimination, error reconstruction, and missing area filling;

[0086] S22: Generate an initial three-dimensional model based on the optimized structural information;

[0087] S23: Perform semantic segmentation processing on the initial three-dimensional model, and based on the semantic segmentation result, reorganize the initial three-dimensional model to obtain the initial tree model for virtual pruning.

[0088] It should be noted that geometric optimization processing refers to performing algorithmic processing on the initially generated three-dimensional structural information to remove redundant point clouds, repair reconstruction errors, and fill in missing data areas, thereby improving the integrity and accuracy of the model. Redundant point cloud elimination is to remove redundant or duplicate point data in the three-dimensional point cloud data, reduce the redundant information of the model, and optimize the calculation efficiency. Error reconstruction refers to correcting geometric errors caused by data noise or limitations of the modeling algorithm to improve the true restoration degree of the model. Missing area filling refers to using interpolation or inference algorithms to supplement unrecorded areas for data missing due to image acquisition angles or occlusions, making the model more complete. Semantic segmentation processing refers to classifying and annotating different parts (such as the trunk, main branches, side branches, and leaves) in the initial three-dimensional model through algorithms, providing structured support for subsequent operations. The initial tree model for virtual pruning refers to a hierarchical three-dimensional model generated through geometric optimization and semantic segmentation, which is used for virtual pruning operations and has a clearer structure and functionality.

[0089] Specifically, through spatial clustering or distance-based filtering algorithms, duplicate points or noisy point clouds are removed to ensure the simplicity and computational efficiency of the model. Errors introduced due to image acquisition accuracy or reconstruction algorithms are corrected, such as adjusting the connection points of branches or repairing distorted parts of the model. For missing areas in the point cloud caused by occlusion or angle problems, methods based on neighboring point interpolation or machine learning inference are used to fill in the missing data. After geometric optimization, an initial three-dimensional model is generated based on the optimized structural information, ensuring that the model has a true scale, accurate spatial distribution, and complete geometric features.

[0090] Furthermore, semantic segmentation processing is performed on the generated initial three-dimensional model to identify and label different structural parts in the model (such as the trunk, main branches, side branches, and leaves). Semantic segmentation can be completed using deep learning-based classification algorithms or rule-driven clustering methods. Subsequently, the model is reorganized according to the results of semantic segmentation to construct a hierarchical three-dimensional model structure. Each level represents different parts of the tree, such as the hierarchical structure of the main trunk and branches, enabling precise positioning and operation of the model in subsequent virtual pruning. Finally, the reorganized model becomes the initial tree model for virtual pruning.

[0091] By eliminating redundant point clouds, correcting errors, and filling in missing areas through geometric optimization, the generated model is more realistic and complete, reducing misjudgments of pruning strategies caused by data problems. Semantic segmentation processing classifies the tree model by functionality, enabling users to accurately select the parts to be pruned and enhancing the intuitiveness and efficiency of operations. The hierarchical model structure supports independent operations on specific levels or parts, making virtual pruning more flexible and meeting different pruning requirements. Automated geometric optimization and semantic segmentation reduce the workload of manual modeling, enabling non-professional users to quickly get started. The optimized initial tree model provides high-quality data input, enhancing the scientific nature and applicability of pruning strategies.

[0092] In this embodiment, based on the multi-angle images and environmental data of the tree to be processed, the three-dimensional structural information of the tree to be processed is determined; based on the three-dimensional structural information, an initial tree model for virtual pruning is generated; the three-dimensional structural information is input into a preset multi-modal pruning inference model to obtain a pruning strategy; based on the pruning strategy, virtual pruning is performed on the initial tree model using AR technology, and the pruned target tree model is displayed in real time. In this embodiment, the three-dimensional structural information is determined through the multi-angle images and environmental data of the tree to be processed, and an initial tree model for virtual pruning is generated to ensure the integrity and accuracy of the data basis for pruning operations; the three-dimensional structural information is input into a preset multi-modal pruning inference model to generate a pruning strategy to clarify the specific positions and methods of pruning; based on the pruning strategy, virtual pruning is performed on the initial tree model using AR technology, and the pruned target tree model is displayed in real time, enabling users to intuitively understand the pruning effect and enhancing the efficiency of tree pruning.

[0093] Based on the above second embodiment, a third embodiment of the tree pruning visualization method of the present application is proposed. Please refer to Figure 3 , Figure 3 which is a schematic diagram of a sub-process in the third embodiment of the tree pruning visualization method of the present application.

[0094] In this embodiment, after step S2, it further includes:

[0095] S2a: Smooth the initial tree model;

[0096] S2b: Based on the sunlight information, adjust the visual effect of the initial tree model after smoothing;

[0097] S2c: Based on a preset rendering engine, perform rendering and visualization processing on the adjusted initial tree model.

[0098] It should be noted that the smoothing process refers to optimizing the surface of a 3D model through algorithms to eliminate uneven or rough parts on the surface, improve the visual quality of the model, and make it closer to the appearance of a real tree. A rendering engine is a graphics processing tool or algorithm framework that is responsible for converting a 3D model into a visual output with lighting, color, and texture effects, making it more realistic and intuitive.

[0099] Specifically, through smoothing filtering or a normal vector-based adjustment method, eliminate surface protrusions or depressions caused by point cloud errors or omissions during the modeling process. While eliminating noise, retain important geometric details (such as bark texture or the natural curvature of branches), ensuring that the model is both smooth and realistic.

[0100] Furthermore, simulate the angle and intensity of sunlight to make the surface of the model present a natural light and dark distribution. Adjust the material reflectivity and color of the tree surface according to the change of light, making it close to the visual performance in the actual environment. The light and shadow effect can be adjusted according to time changes to present the dynamic appearance of the tree under different sunlight conditions. Simulate the real light and shadow effect of the tree in the environment through a global illumination algorithm. Add texture maps and detailed textures (such as bark texture and the reflective effect of leaves) to the model to enhance the authenticity of the model. Output the rendered model to the user interface to support the user to view and interact with the model from multiple angles, such as zooming in, zooming out, or rotating the model, further enhancing the intuitiveness of virtual pruning.

[0101] Through smoothing and lighting adjustment, the surface of the model becomes smoother and more delicate, and the lighting effect is more realistic, providing users with a high-quality visual experience. Based on the dynamic lighting adjustment and material optimization of sunlight information, the performance of the model under different environmental conditions is closer to the real scene, enhancing the user's operation immersion. The clear visualization effect generated by the rendering engine helps users understand the tree structure more intuitively, providing a clear basis for the selection and adjustment of pruning plans. Through dynamic rendering, the model can adapt to different lighting environments and meet the needs of diverse pruning scenarios. The optimized model effect enables users to easily understand the tree structure and pruning effect without professional knowledge, reducing the usage threshold.

[0102] Based on the above second embodiment, in this embodiment, step S4 includes:

[0103] S41: Analyze the pruning strategy to determine the recommended pruning position, recommended cutting angle, and recommended pruning time;

[0104] S42: When a pruning confirmation instruction is obtained, based on the recommended pruning position, the recommended cutting angle, and the recommended pruning time, use AR technology to virtually prune the initial tree model;

[0105] S43: Use a preset dynamic rendering algorithm to render the initial tree model after virtual pruning to obtain a target tree model, and display the pruned target tree model in real time.

[0106] It should be noted that the recommended pruning position refers to the specific branches or tree parts marked in the pruning strategy that need to be removed or adjusted to optimize the tree structure. The recommended cutting angle refers to the angle between the tool and the target branch during pruning, which affects the pruning effect and the wound recovery of the tree. The recommended pruning time is the optimal pruning period (such as a certain season or a specific time of day) derived by combining the tree growth cycle and environmental data to ensure the scientific nature of pruning. The dynamic rendering algorithm is a graphics processing algorithm that updates and renders the lighting, texture, and structural changes of the tree model in real time according to the pruning operation to generate the visual effect after pruning.

[0107] Specifically, analyze the pruning strategy generated by the multi-modal pruning inference model. Determine the specific branches or parts that need to be removed or adjusted and highlight them in the form of virtual marks in the initial tree model. Calculate the optimal cutting angle to ensure that the pruning can remove the target part while minimizing the damage to the tree to the greatest extent. Optimize the pruning period according to environmental data (such as season, humidity) to ensure that the operation is carried out when the tree's growth and recovery ability is the strongest. Users view the pruning suggestions through the device interface and confirm whether to accept the recommended pruning plan. After the user confirms, enter the pruning execution stage.

[0108] Furthermore, the system displays the positions and cutting directions of the branches to be pruned in an augmented reality manner from the user's perspective. Remove the virtual branches at the recommended positions according to the pruning instructions, and update the 3D model in real time to present the pruning process and stage effects. Calculate the lighting and shadow effects of the model after pruning in real time to simulate the impact of natural light on the tree form. Adjust the surface texture of the pruning area (such as the color or reflectivity of the wound) to enhance the realism of the model. Generate the target tree model after pruning, and the user can view the pruning effect from multiple angles and compare it with the model before pruning. Finally, the target tree model is displayed in real time on the user interface for the user to evaluate the pruning results or adjust the next operation.

[0109] By parsing the pruning strategy and highlighting the recommended positions and cutting angles, the user can quickly locate the parts that need to be pruned and avoid misoperations. Combining the recommended pruning time ensures that the operation conforms to the growth law of the tree and improves the positive effect of pruning on the tree health. Using AR technology and dynamic rendering algorithms to display the pruning effect in real time enables the user to quickly evaluate and adjust the pruning strategy, reducing the trial-and-error cost. Through virtual pruning, the user can intuitively understand the pruning process and target effect, and even non-professional users can easily complete high-quality operations. The dynamic rendering algorithm provides realistic lighting and texture changes for the pruning area, making the target tree model visually closer to the actual pruning result. Integrating pruning strategy parsing, virtual execution, and effect display into one realizes seamless connection from decision-making to operation to feedback, significantly improving the pruning efficiency.

[0110] Based on the above second embodiment, in this embodiment, after step S4, it further includes:

[0111] S4a: When receiving a pruning modification instruction, based on the pruning modification instruction, adjust the recommended pruning position, the recommended cutting angle, and the recommended pruning time;

[0112] S4b: Based on the adjusted recommended pruning position, the recommended cutting angle, and the recommended pruning time, use AR technology to perform virtual pruning on the initial tree model and display the initial tree model after pruning;

[0113] S4c: Obtain interactive evaluation data, and optimize the preset multi-modal pruning inference model based on the interactive evaluation data.

[0114] It should be noted that the pruning modification instruction is an adjustment instruction proposed by the user based on their own needs or actual observations after viewing the pruning suggestions, and is used to modify the recommended pruning position, cutting angle, or pruning time. The recommended pruning position refers to the branches or tree parts to be pruned suggested by the model, and the target position can be changed after adjustment. The recommended cutting angle is the cutting direction and angle suggested by the model, which is used to control the pruning accuracy; the impact on the tree can be optimized after adjustment. The recommended pruning time is the pruning execution time period suggested based on environmental data, and it can be adjusted to adapt to specific growth conditions or user needs. The interactive evaluation data refers to the feedback information submitted by the user after completing the virtual pruning operation, such as the satisfaction with the pruning effect, adjustment suggestions, etc. The multi-modal pruning inference model is an artificial intelligence model that generates pruning strategies by integrating multiple data (such as three-dimensional structure information, environmental data, and user feedback); through optimization, its prediction accuracy and adaptability are improved.

[0115] Specifically, modify the branches or tree parts to be pruned according to the user's instructions, such as adding or removing pruning marks for certain branches. Change the recommended cutting angle to better meet the user's expectations or actual operating conditions. Modify the time suggestion according to the user's needs, and re-evaluate the best pruning time period in combination with the updated environmental data. After the adjustment is completed, based on the modified pruning suggestions, use AR technology to perform virtual pruning on the initial tree model. The pruning process is visually displayed on the user's device, including real-time cutting animations and dynamically updated model structures.

[0116] Furthermore, after completing the virtual pruning and displaying the updated initial tree model, the system obtains the user's interactive evaluation data, such as: scoring the effect of the pruned model; submitting opinions on the accuracy or applicability of the pruning suggestions; providing specific suggestions on whether further optimization is needed. The collected interactive evaluation data is uploaded to the cloud for optimizing the multi-modal pruning inference model. The specific ways of model optimization can be: data augmentation: expanding the training dataset by combining user feedback and adding new samples to improve the generality of the model; model weight adjustment: re-training or fine-tuning the model weights based on user feedback to make it more in line with the user's actual needs and operation preferences; online learning mechanism: adopting a real-time update method to enable the model to continuously learn new data and continuously improve the accuracy of the pruning strategy.

[0117] By receiving the user's pruning modification instructions, the system can dynamically adjust the pruning suggestions to meet the user's personalized needs and avoid rigid solutions. The adjustment of the pruning suggestions combines the user's experience and the feedback of the actual scenario, further improving the accuracy of the pruning position, cutting angle, and time selection. The adjusted effect is displayed in real time through virtual pruning, enabling the user to quickly verify whether the modified solution meets the expectations. The introduction of interactive evaluation data provides an important reference for model optimization, enhancing the prediction ability of the model through an online learning mechanism to make it more in line with the actual needs of users. Combining user feedback and environmental data to dynamically adjust the pruning strategy makes the pruning decision more scientific and reasonable, adapting to different scenarios and tree conditions. Allowing users to actively participate in the adjustment process of pruning suggestions improves the user's satisfaction with the pruning effect and at the same time reduces the operation threshold for non-professional users.

[0118] In this embodiment, based on the multi-angle images and environmental data of the tree to be processed, the three-dimensional structure information of the tree to be processed is determined; based on the three-dimensional structure information, an initial tree model for virtual pruning is generated; the three-dimensional structure information is input into a preset multi-modal pruning inference model to obtain a pruning strategy; based on the pruning strategy, the initial tree model is virtually pruned using AR technology, and the pruned target tree model is displayed in real time. In this embodiment, the three-dimensional structure information is determined through the multi-angle images and environmental data of the tree to be processed, and an initial tree model for virtual pruning is generated, ensuring the integrity and accuracy of the data basis for pruning operations; the three-dimensional structure information is input into a preset multi-modal pruning inference model to generate a pruning strategy to clarify the specific position and method of pruning; based on the pruning strategy, the initial tree model is virtually pruned using AR technology, and the pruned target tree model is displayed in real time, enabling the user to intuitively understand the pruning effect and improving the efficiency of tree pruning.

[0119] An embodiment of the present application also provides a tree pruning visualization device. Please refer to Figure 4 , Figure 4 , which is a schematic module structure diagram of the tree pruning visualization device of the embodiment of the present application, including:

[0120] A structure determination module 401, configured to determine the three-dimensional structure information of the tree to be processed according to the multi-angle images and environmental data of the tree to be processed;

[0121] A model generation module 402, configured to generate an initial tree model for virtual pruning based on the three-dimensional structure information;

[0122] A strategy generation module 403, configured to input the three-dimensional structure information into a preset multi-modal pruning inference model to obtain a pruning strategy;

[0123] A target module 404, configured to virtually prune the initial tree model using AR technology based on the pruning strategy and display the pruned target tree model in real time.

[0124] The tree pruning visualization device provided by the embodiment of the present application adopts the tree pruning visualization method in the above embodiment, and can solve the technical problem of how to improve the tree pruning efficiency. Compared with the prior art, the beneficial effects of the tree pruning visualization device provided by the embodiment of the present application are the same as those of the tree pruning visualization method provided by the above embodiment, and other technical features in the tree pruning visualization device are the same as the features disclosed in the method of the above embodiment, which will not be elaborated here.

[0125] The present application provides a tree pruning visualization device, which includes: at least one processor; and a memory communicatively connected to the at least one processor; wherein, the memory stores instructions executable 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 execute the tree pruning visualization method in the above embodiment.

[0126] Next, refer to Figure 5 , Figure 5 which is a schematic structural diagram of a device for the hardware operating environment involved in the tree pruning visualization method in the embodiment of the present application, and shows a schematic structural diagram of a device suitable for implementing the tree pruning visualization device in the embodiment of the present application. The tree pruning visualization device in the embodiment of the present application may include, but is not limited to, mobile terminals such as mobile phones, laptop computers, digital broadcast receivers, PDAs (Personal Digital Assistants), PADs (Portable Application Descriptions), PMPs (Portable Media Players), in-vehicle terminals (such as in-vehicle navigation terminals), etc., and fixed terminals such as digital TVs, desktop computers, etc. Figure 5 The shown tree pruning visualization device is only an example and should not impose any limitation on the functions and usage scope of the embodiment of the present application.

[0127] Such as Figure 5As shown, the tree pruning visualization device may include a processing device 1001 (such as a central processing unit, a graphics processing unit, etc.), which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM: Read Only Memory) 1002 or a program loaded from a storage device 1003 into a random access memory (RAM: Random Access Memory) 1004. In the RAM 1004, various programs and data required for the operation of the tree pruning visualization device are also stored. The processing device 1001, the ROM 1002, and the RAM 1004 are connected to each other through a bus 1005. An input / output (I / O) interface 1006 is also connected to the bus. Generally, the following systems can be connected to the I / O interface 1006: an input device 1007 including, for example, a touch screen, a touchpad, a keyboard, a mouse, an image sensor, a microphone, an accelerometer, a gyroscope, etc.; an output device 1008 including, for example, a liquid crystal display (LCD: Liquid Crystal Display), a speaker, a vibrator, etc.; a storage device 1003 including, for example, a magnetic tape, a hard disk, etc.; and a communication device 1009. The communication device 1009 can allow the tree pruning visualization device to communicate with other devices wirelessly or wiredly to exchange data. Although the figure shows a tree pruning visualization device having various systems, it should be understood that it is not required to implement or have all the shown systems. Instead, more or fewer systems can be implemented or had.

[0128] In particular, according to the embodiments disclosed in the present application, the processes described above with reference to the flowcharts can be implemented as computer software programs. For example, the embodiments disclosed in the present application include a computer program product, which includes a computer program carried on a computer-readable medium, and the computer program contains program codes for executing the methods shown in the flowcharts. In such an embodiment, the computer program can be downloaded and installed from a network through the communication device, or installed from the storage device 1003, or installed from the ROM 1002. When the computer program is executed by the processing device 1001, the above functions defined in the methods of the embodiments disclosed in the present application are executed.

[0129] The tree pruning visualization device provided by the present application adopts the tree pruning visualization method in the above embodiments and can solve the technical problem of how to improve the efficiency of tree pruning. Compared with the prior art, the beneficial effects of the tree pruning visualization device provided by the present application are the same as those of the tree pruning visualization method provided by the above embodiments, and other technical features in the tree pruning visualization device are the same as those disclosed in the method of the previous embodiment, and will not be elaborated here.

[0130] It should be understood that each part disclosed in this application can be implemented by hardware, software, firmware or a combination thereof. In the description of the above embodiments, specific features, structures, materials or characteristics can be combined in a suitable manner in any one or more embodiments or examples.

[0131] As described above, the above are only specific embodiments of this application, but the protection scope of this application is not limited thereto. Any person skilled in the art within the technical scope disclosed in this application can easily think of changes or substitutions, which should all be covered within the protection scope of this application. Therefore, the protection scope of this application should be subject to the protection scope of the claims.

[0132] This application provides a computer-readable storage medium with computer-readable program instructions (i.e., computer programs) stored thereon, and the computer-readable program instructions are used to execute the tree pruning visualization method in the above embodiments.

[0133] The computer-readable storage medium provided by this application can be, for example, a USB flash drive, but is not limited to electrical, magnetic, optical, electromagnetic, infrared, or semiconductor systems, devices, or any combination of the above. More specific examples of computer-readable storage media can include, but are not limited to: electrical connections with one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM) or flash memory, optical fibers, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination of the above. In this embodiment, the computer-readable storage medium can be any tangible medium that contains or stores a program, and this program can be used by or combined with an instruction execution system, device, or device. The program code contained on the computer-readable storage medium can be transmitted by any appropriate medium, including but not limited to: wires, optical cables, RF (Radio Frequency), etc., or any suitable combination of the above.

[0134] The above computer-readable storage medium may be included in the tree pruning visualization device; or it may exist independently without being assembled into the tree pruning visualization device. The above computer-readable storage medium carries one or more programs. When the above one or more programs are executed by the tree pruning visualization device, the tree pruning visualization device is enabled to: determine the three-dimensional structure information of the tree to be processed according to the multi-angle images and environmental data of the tree to be processed; generate an initial tree model for virtual pruning based on the three-dimensional structure information; input the three-dimensional structure information into a preset multi-modal pruning inference model to obtain a pruning strategy; based on the pruning strategy, use AR technology to perform virtual pruning on the initial tree model and display the pruned target tree model in real time. Computer program code for performing the operations of the present application may be written in one or more programming languages or combinations thereof. The above programming languages include object-oriented programming languages - such as Java, Smalltalk, C++; and also include conventional procedural programming languages - such as the "C" language or similar programming languages. The program code may be executed entirely on the user's computer, partially on the user's computer, executed as a stand-alone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer through any type of network - including a local area network (LAN) or a wide area network (WAN), or it may be connected to an external computer (for example, by using an Internet service provider to connect through the Internet).

[0135] The flowcharts and block diagrams in the accompanying drawings illustrate the possible architectures, functions, and operations of systems, methods, and computer program products according to various embodiments of the present application. In this regard, each block in the flowchart or block diagram may represent a module, a program segment, or a part of code that contains one or more executable instructions for implementing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the blocks may occur in a different order than marked in the accompanying drawings. For example, two consecutive blocks shown may actually be executed substantially in parallel, and they may sometimes be executed in the reverse order, depending on the functions involved. It should also be noted that each block in the block diagram and / or flowchart, and the combination of blocks in the block diagram and / or flowchart, may be implemented by a dedicated hardware-based system for performing the specified functions or operations, or may be implemented by a combination of dedicated hardware and computer instructions.

[0136] The modules involved in the embodiments of the present application can be implemented in software or in hardware. Among them, the name of the module does not constitute a limitation on the unit itself in some cases.

[0137] The readable storage medium provided by the present application is a computer-readable storage medium, and the computer-readable storage medium stores computer-readable program instructions (i.e., computer programs) for executing the above-mentioned tree pruning visualization method, which can solve the technical problem of how to improve the efficiency of tree pruning. Compared with the prior art, the beneficial effects of the computer-readable storage medium provided by the present application are the same as those of the tree pruning visualization method provided by the above embodiments, and will not be elaborated here.

[0138] The embodiments of the present application provide a computer program product, including a computer program, and the steps of the above-mentioned tree pruning visualization method are implemented when the computer program is executed by a processor.

[0139] The computer program product provided by the present application can solve the technical problem of how to improve the efficiency of tree pruning. Compared with the prior art, the beneficial effects of the computer program product provided by the embodiments of the present application are the same as those of the tree pruning visualization method provided by the above embodiments, and will not be elaborated here.

[0140] The above are only the preferred embodiments of the present application, and do not limit the patent scope of the present application. Any equivalent structure or equivalent process transformation made by using the specification and drawings of the present application, or directly or indirectly applied in other related technical fields, shall be equally included in the patent scope of the present application.

Claims

1. A tree pruning visualization method, characterized in that: The method comprises: Determining three-dimensional structural information of the trees to be treated based on multi-angle images and environmental data of the trees to be treated; Based on the three-dimensional structure information, generating an initial tree model for virtual pruning; Inputting the three-dimensional structure information into a preset multimodal pruning reasoning model to obtain a pruning strategy; Based on the pruning strategy, the initial tree model is virtually pruned using AR technology, and the pruned target tree model is displayed in real time.

2. The method according to claim 1, characterized in that The step of determining the three-dimensional structural information of the tree to be processed based on the multi-angle images and environmental data of the tree to be processed comprises: Acquire multi-angle images and environmental data of the trees to be processed, wherein the environmental data includes geographical location information, temperature information, humidity information, and sunshine information; Preprocessing the multi-angle images to obtain preprocessed images, wherein the preprocessing includes one or more of denoising, alignment, and image segmentation; Extracting key feature points of the preprocessed image based on a preset deep learning algorithm; The three-dimensional structural information of the tree to be processed is determined according to the key feature points and the environmental data.

3. The method according to claim 2, characterized in that The step of generating an initial tree model for virtual pruning based on the three-dimensional structure information comprises: Performing geometric optimization processing on the three-dimensional structure information to obtain optimized structure information, wherein the geometric optimization processing includes one or more of redundant point cloud elimination, error reconstruction, and missing area filling; Based on the optimized structural information, an initial three-dimensional model is generated; The initial three-dimensional model is subjected to semantic segmentation processing, and the initial three-dimensional model is reorganized according to the semantic segmentation result to obtain the initial tree model for virtual pruning.

4. The method according to claim 3, characterized in that After the step of generating an initial tree model for virtual pruning based on the three-dimensional structure information, the method further includes: Performing smoothing on the initial tree model; Based on the sunlight information, adjusting the visual effect of the initial tree model after smoothing; Based on a preset rendering engine, the adjusted initial tree model is rendered and visualized.

5. The method according to claim 1, characterized in that The step of using AR technology to virtually prune the initial tree model based on the pruning strategy and displaying the pruned target tree model in real time includes: Analyzing the pruning strategy to determine a recommended pruning position, a recommended cutting angle, and a recommended pruning time; When a pruning confirmation instruction is obtained, the initial tree model is virtually pruned using AR technology based on the recommended pruning position, the recommended cutting angle, and the recommended pruning time; The preset dynamic rendering algorithm is used to render the initial tree model after virtual pruning to obtain the target tree model, and the pruned target tree model is displayed in real time.

6. The method according to claim 5, characterized in that After the step of virtually pruning the initial tree model using AR technology based on the pruning strategy and displaying the pruned target tree model in real time, the method further includes: When receiving a trimming modification instruction, adjusting the recommended trimming position, the recommended cutting angle, and the recommended trimming time based on the trimming modification instruction; Based on the adjusted recommended pruning position, the recommended cutting angle, and the recommended pruning time, the initial tree model is virtually pruned using AR technology, and the pruned initial tree model is displayed; Acquire interactive evaluation data, and optimize the preset multimodal pruning inference model based on the interactive evaluation data.

7. A tree pruning visualization device, characterized in that: The device comprises: A structure determination module, used to determine the three-dimensional structure information of the tree to be processed based on the multi-angle images and environmental data of the tree to be processed; A model generation module, used to generate an initial tree model for virtual pruning based on the three-dimensional structure information; A strategy generation module, used for inputting the three-dimensional structure information into a preset multimodal pruning reasoning model to obtain a pruning strategy; The target module is used to virtually prune the initial tree model based on the pruning strategy using AR technology, and to display the pruned target tree model in real time.

8. A computer device, characterized in that: The device comprises: a memory, a processor, and a tree pruning visualization program stored in the memory and executable on the processor, wherein the tree pruning visualization program is configured to implement the steps of the tree pruning visualization method according to any one of claims 1 to 6.

9. A storage medium, characterized in that: The storage medium stores a tree pruning visualization program, and when the tree pruning visualization program is executed by a processor, the steps of the tree pruning visualization method according to any one of claims 1 to 6 are implemented.

10. A computer program product, characterized in that The computer program product comprises a computer program, which, when executed by a processor, implements the steps of the tree pruning visualization method according to any one of claims 1 to 6.

Images