Agricultural teaching method, system and equipment based on virtual reality technology and medium

Abstract

The invention discloses an agricultural teaching method, system and device based on a virtual reality technology, and a medium, and relates to the technical field of virtual reality and agricultural education. According to the method, a dynamic virtual scene is generated based on three-dimensional geographic information data and a plant morphological feature library; dynamically simulating life cycle changes of the target object through a plant growth dynamics algorithm, the changes including organ morphological evolution and physiological index changes of the target object; obtaining a multi-modal interaction signal, and generating a control instruction for the dynamic virtual scene according to the multi-modal interaction signal; adjusting environmental parameters in the growth environment and the target object according to the control instruction to obtain a dynamic simulation result; and rendering the dynamic simulation result in real time through a three-dimensional visualization engine, and generating an interactive interface of the target object. By implementing the technical scheme provided by the invention, the effect of improving teaching interactivity is achieved.

Description

Technical Field

[0001] The present invention relates to the field of virtual reality and agricultural education technology, and in particular to an agricultural teaching method, system, equipment and storage medium based on virtual reality technology. Background Art

[0002] Virtual reality (VR) technology has undergone decades of development, from its inception in the 1960s to its initial adoption in gaming in the 1990s, and then to its explosive growth in the 21st century. It is now widely used in education, healthcare, entertainment, and other fields. In the future, VR will evolve towards lightweight, wireless, and intelligent features. In education, in particular, it is expected to reshape traditional teaching models through dynamic interaction and intelligent assessment.

[0003] Current agricultural education systems often use static 3D models or pre-rendered animations to demonstrate plant growth. These systems use a pre-set rule library to drive organ morphological changes and employ simplified algorithms to simulate material distribution. These systems lack a real-time coupling mechanism between environmental parameters and physiological indicators, making dynamic control in complex scenarios difficult.

[0004] Therefore, there is an urgent need for an agricultural teaching method that can improve teaching interactivity and enhance user experience. Summary of the Invention

[0005] In order to improve teaching interactivity and user experience, the present application provides an agricultural teaching method, system, equipment and medium based on virtual reality technology.

[0006] In a first aspect of the present application, an agricultural teaching method based on virtual reality technology is provided, which adopts the following technical solutions: Generate a dynamic virtual scene based on three-dimensional geographic information data and a plant morphological feature library, wherein the dynamic virtual scene includes a target object and a growth environment of the target object; Dynamically simulate the life cycle changes of the target object through a plant growth dynamics algorithm, wherein the changes include the organ morphological evolution and physiological index changes of the target object; Acquiring a multimodal interaction signal, and generating a control instruction for the dynamic virtual scene according to the multimodal interaction signal; Adjusting environmental parameters in the growth environment and the target object according to the control instruction to obtain a dynamic simulation result; The dynamic simulation results are rendered in real time through a three-dimensional visualization engine to generate an interactive interface for the target object.

[0007] By adopting the above technical solutions, dynamic scene generation based on three-dimensional geographic information and plant morphology library can accurately restore the real growth environment of crops, improve the credibility of the scene and the sense of learning immersion; through the full life cycle simulation driven by the plant growth dynamics algorithm, the evolution of organ morphology and the dynamic changes of physiological indicators are displayed in real time, helping users to intuitively understand the crop growth mechanism; multimodal interaction supports natural control methods such as voice and gestures, combined with the dynamic adjustment function of environmental parameters to achieve closed-loop teaching; the rendering technology of the three-dimensional visualization engine ensures that the simulation results respond quickly, forming an interactive learning chain, and significantly improving the efficiency of agricultural knowledge transfer and the quality of practical ability training.

[0008] Optionally, generating a dynamic virtual scene based on the three-dimensional geographic information data and the plant morphological feature library includes: Acquiring the three-dimensional geographic information data, including terrain elevation, slope, aspect, terrain curvature data, surface relief type, and surface cover type; Based on the type of the target object, calling the species-specific model in the plant morphological feature library to generate a distribution model of the target object, the distribution model including geometric structure parameters, texture characteristics and root distribution of the target object organ; The three-dimensional geographic information data is integrated with the distribution model to generate the dynamic virtual scene.

[0009] By adopting the above technical solutions, the construction and dynamic coupling simulation of high-precision agricultural virtual scenes have been realized: first, multi-dimensional geographic data such as terrain elevation, slope, curvature, and surface cover types are integrated to construct a surface base that is close to reality; second, based on the species-specific models in the plant morphological feature library, three-dimensional crop models containing organ geometry, texture characteristics and root distribution are dynamically generated to ensure the scientific nature of morphological simulation; then, through the deep integration of terrain and plant models, ecological processes such as light distribution and soil erosion are calculated in real time, forming a dynamic interaction between environmental parameters and biological growth; finally, multi-scale teaching scenarios from macro-terrain analysis to micro-organ observation are supported, significantly improving the scene immersion and teaching effectiveness.

[0010] Optionally, the step of fusing the three-dimensional geographic information data with the distribution model to generate the dynamic virtual scene further includes: adjusting the distribution model according to the slope aspect, and matching the canopy morphology of the target object with the surface undulation type through geometric mapping technology to obtain a topological structure map, wherein the canopy morphology refers to the three-dimensional structural characteristics formed by the above-ground part of the plant; Retrieving a preset nutrient absorption efficiency database based on the surface cover type to generate input parameters for nutrient uptake of the target object; Dynamically correcting the growth direction vector of the target organ according to the terrain curvature data; The topological structure diagram, the input parameters and the growth direction vector are coupled with the terrain elevation through a three-dimensional engine for rendering to generate the dynamic virtual scene.

[0011] By adopting the above technical solutions, the distribution model is dynamically adjusted based on the slope, and the canopy morphology is accurately matched with the surface undulations through geometric mapping to form an ecological scene with a real topological structure; the nutrient absorption parameters are intelligently matched in combination with the surface cover type to build an environmental and physiological coupling mechanism; the terrain curvature is used to correct the organ growth direction vector in real time to simulate the influence of gravity and microtopography on plant morphology; the topological structure, nutrient parameters, growth vector and terrain elevation are multi-field coupled and rendered through a three-dimensional engine to form a dynamic virtual scene with environmental adaptability. This solution not only enhances the visualization accuracy of agricultural ecological processes, but also supports learners to understand the interaction mechanism between crops and the environment from multiple dimensions such as terrain, nutrients, and gravity, significantly improving the immersive teaching effect. Optionally, the dynamically simulating the lifecycle changes of the target object further includes: determining a first developmental stage of an organ of the target object according to the type of the target object; Integrating the correlation parameters between the changes in the physiological indicators and the evolution of the organ morphology to establish a dynamic function between the carbon and nitrogen distribution ratio and the stem elongation rate of the target object; According to the dynamic function, the morphological change of the organ of the target object in the first developmental stage is driven.

[0012] By adopting the above technical solutions, we first drive the evolution of organ morphology by constructing a dynamic model of carbon and nitrogen distribution, and couple physiological metabolism with three-dimensional structural feedback in real time to accurately simulate the dynamic response of plant phenotypic plasticity to environmental conditions. Based on the species-specific developmental stage division, the photosynthetic product regulation mechanism is quantified, supporting learners to interactively explore the regulatory laws of light / nutrient changes on phenotypic characteristics such as stem elongation and leaf expansion, significantly improving the scientific rigor and practical decision-making efficiency of crop growth mechanism simulation in agricultural education scenarios.

[0013] Optionally, the acquiring of the multimodal interaction signal and generating a control instruction for the dynamic virtual scene according to the multimodal interaction signal further comprises: Acquiring a spatial gesture signal, and parsing the spatial gesture signal into an adjustment instruction for the target organ of the target object and the growth environment; Recognizing semantic features in the voice command, and mapping the semantic features into parameters of the growth environment and adjustment values of the target organ; Locating a gaze point through eye tracking, and generating a dynamic monitoring request for changes in the physiological indicators of a target area of the target object according to the gaze point; Acquiring pressure sensing data from a force feedback device, and generating a physical deformation adjustment instruction for the target organ according to the pressure sensing data; The adjustment instruction, the adjustment value, the dynamic monitoring request and the physical deformation adjustment instruction are integrated to generate the control instruction.

[0014] By adopting the above technical solutions, spatial gesture recognition supports direct manipulation of organ morphology and environmental parameters, improving the naturalness of interaction; voice recognition automatically maps semantic features to environmental parameter adjustments, realizing multi-dimensional control driven by voice commands; eye tracking instantly generates physiological indicator monitoring requests, enhancing data acquisition efficiency and guiding learners' focus; force feedback devices convert physical pressure into organ deformation instructions, providing tactile interaction authenticity; multimodal signal integration realizes multi-directional collaborative control, significantly improving operational accuracy and learning efficiency in agricultural education scenarios.

[0015] Optionally, adjusting the environmental parameters in the growth environment and the target object according to the control instruction to obtain a dynamic simulation result further includes: parsing the adjustment value in the control instruction and updating the multidimensional parameter set of the growth environment, the multidimensional parameter set including temperature gradient, humidity distribution, light intensity spectrum and soil moisture content; Calculating the physiological state of the target object based on the updated multidimensional parameter set using the organ-level physiological response model of the target object, the physiological state including stomatal conductance, transpiration rate, photosynthesis efficiency, and stress resistance factor; Establishing a dynamic mapping relationship between the variation of the multidimensional parameter set and the organ morphological parameter, and based on the dynamic mapping relationship, driving the target object organ to evolve in coordination with the physiological state; When any environmental parameter exceeds a first threshold, the morphological features of the target organ and the corresponding timestamp are recorded to generate an environmental stress response data set; The updated multi-dimensional parameter set is spatially aligned with the morphological features of the target organ to obtain the dynamic simulation result.

[0016] By employing this technical solution, multidimensional environmental parameters such as temperature gradients and humidity distribution are dynamically controlled, and combined with organ-level physiological response models to form a real-time, two-way feedback mechanism. The system automatically updates crop physiological status based on changes in environmental parameters and drives the coordinated evolution of crop organ morphology and environmental conditions. When environmental parameters exceed thresholds, organ morphological characteristics and time-series data are automatically recorded to generate an environmental stress response dataset. This provides quantitative support for research on stress resistance mechanisms and significantly enhances the accuracy of ecological process simulations and the depth of teaching demonstrations.

[0017] Optionally, generating an interactive interface for the target object further includes: Mapping the environmental parameters of the growth environment into a three-dimensional thermal map, and encoding the physiological indicators of the target object into an organ-level color scale map; Determining the spatial coordinates of the organs of the target object by a ray casting algorithm, associating the spatial coordinates of the organs with physiological parameters and a historical growth database, and generating organ-level data visualization labels; When the environmental parameter exceeds a second threshold, generating a dynamic control strategy based on a plant stress resistance model, the dynamic control strategy including a light environment adjustment parameter and a microclimate control scheme; The three-dimensional thermal map, the organ-level data visualization label and the dynamic control strategy are spatially aligned to generate the interactive interface.

[0018] By adopting the above technical solution, a three-dimensional thermal map is used to intuitively map the spatial distribution of environmental parameters, combined with organ-level color-scale maps to encode physiological indicators, achieving multi-source data fusion and visualization. A ray casting algorithm is used to generate organ spatial coordinate labels, linking them to a historical growth database in real time, allowing users to interactively query organ development trajectories. When environmental risks exceed the threshold, the system leverages the stress resistance model to generate dynamic control strategies. Spatial registration technology then overlays these strategy parameters onto the virtual scene, creating a closed-loop interaction that significantly enhances learning scenario immersion and practical decision-making efficiency.

[0019] In a second aspect of the present application, an agricultural teaching system based on virtual reality technology is provided, specifically comprising: A scene generation module, configured to generate a dynamic virtual scene based on three-dimensional geographic information data and a plant morphological feature library, wherein the dynamic virtual scene includes a target object and a growth environment of the target object; An evolution module, configured to dynamically simulate the life cycle changes of the target object through a plant growth dynamics algorithm, wherein the changes include the organ morphology evolution and physiological index changes of the target object; An instruction generation module, configured to obtain a multimodal interaction signal and generate a control instruction for the dynamic virtual scene according to the multimodal interaction signal; A dynamic simulation module, configured to adjust environmental parameters in the growth environment and the target object according to the control instruction to obtain a dynamic simulation result; The visualization module is used to render the dynamic simulation results in real time through a three-dimensional visualization engine to generate an interactive interface for the target object.

[0020] In the third aspect of the present application, an electronic device is provided, including a processor, a memory, a user interface and a network interface, the memory is used to store instructions, the user interface and the network interface are both used to communicate with other devices, and the processor is used to execute the instructions stored in the memory so that the electronic device performs any of the methods described above.

[0021] In a fourth aspect of the present application, a computer-readable storage medium is provided, wherein the computer-readable storage medium stores instructions. When the instructions are executed, any one of the methods described above is executed.

[0022] In summary, one or more technical solutions provided in the embodiments of the present application have at least the following technical effects or advantages: By integrating three-dimensional geographic information with a plant morphology library to construct high-precision dynamic scenes, and combining plant growth dynamics algorithms to achieve full-life cycle coupled simulation of organ morphology and physiological indicators, the system significantly enhances scene restoration and teaching immersion. Innovative multimodal interaction technology integrates gestures, voice, eye movements, and force feedback devices to build a closed-loop teaching chain, supporting real-time dynamic responses of environmental parameters and crop phenotypes. Based on organ-level physiological models, the system calculates key indicators such as stomatal conductance in real time, drives crop-environment co-evolution, and automatically generates stress response data sets. The three-dimensional visualization engine maps environmental parameters into thermal maps, encodes physiological indicators into color-scale maps, and superimposes dynamic control strategies to form an intelligent interactive interface, significantly improving the efficiency of visual analysis of agricultural mechanisms and practical decision-making support capabilities, providing a high-reliability digital twin platform for agricultural education. BRIEF DESCRIPTION OF THE DRAWINGS

[0023] Figure 1 This is a schematic diagram of the system architecture of an embodiment of an agricultural teaching method or system based on virtual reality technology of the present application; Figure 2 This is a flowchart of an agricultural teaching method based on virtual reality technology disclosed in an embodiment of the present application; Figure 3 This is a module diagram of an agricultural teaching system based on virtual reality technology disclosed in an embodiment of the present application; Figure 4 This is a schematic structural diagram of an electronic device disclosed in an embodiment of the present application.

[0024] Explanation of the accompanying drawings: 301, scene generation module; 302, evolution module; 303, instruction generation module; 304, dynamic simulation module; 305, visualization module; 401, processor; 402, communication bus; 403, user interface; 404, network interface; 405, memory. DETAILED DESCRIPTION

[0025] In order to enable those skilled in the art to better understand the technical solutions in this specification, the technical solutions in the embodiments of this specification will be clearly and completely described below in conjunction with the drawings in the embodiments of this specification. Obviously, the described embodiments are only part of the embodiments of this application, not all of the embodiments.

[0026] In the description of the embodiments of this application, words such as "for example" or "for instance" are used to indicate examples, illustrations, or explanations. Any embodiment or design described as "for example" or "for instance" in the embodiments of this application should not be construed as being preferred or advantageous over other embodiments or designs. Rather, the use of words such as "for example" or "for instance" is intended to present the relevant concepts in a concrete manner.

[0027] In the description of the embodiments of the present application, the term "multiple" means two or more. For example, multiple systems refer to two or more systems, and multiple screen terminals refer to two or more screen terminals. In addition, the terms "first" and "second" are used for descriptive purposes only and are not to be understood as indicating or implying relative importance or implicitly indicating the indicated technical features. Thus, the features defined as "first" and "second" may explicitly or implicitly include one or more of the features. The terms "including", "comprising", "having" and their variations all mean "including but not limited to", unless otherwise specifically emphasized.

[0028] like Figure 1 As shown, system architecture 100 may include terminal devices 101, 102, 103, a network 104, and a server 105. Network 104 is a medium for providing communication links between terminal devices 101, 102, 103 and server 105. Network 104 may include various connection types, such as wired or wireless communication links or fiber optic cables.

[0029] Users can use terminal devices 101, 102, and 103 to interact with server 105 via network 104 to receive or send messages, etc. Various communication client applications can be installed on terminal devices 101, 102, and 103, such as model training applications, video recognition applications, web browser applications, social platform software, etc.

[0030] Terminal devices 101, 102, and 103 can be hardware or software. When terminal devices 101, 102, and 103 are hardware, they can be various electronic devices with display screens, including but not limited to smartphones, tablet computers, e-book readers, MP3 (Moving Picture Experts Group Audio Layer III, Moving Picture Experts Group Audio Layer 3) players, MP4 (Moving Picture Experts Group Audio Layer IV, Moving Picture Experts Group Audio Layer 4) players, laptop computers, and desktop computers, etc. When terminal devices 101, 102, and 103 are software, they can be installed in the electronic devices listed above. They can be implemented as multiple software or software modules (for example, multiple software or software modules used to provide distributed services), or they can be implemented as a single software or software module. No specific limitation is made here.

[0031] When terminals 101, 102, and 103 are hardware, they may also be equipped with a video capture device. The video capture device may be any device capable of capturing video, such as a camera, a sensor, and the like. Users can use the video capture device on terminals 101, 102, and 103 to capture video.

[0032] The server 105 may be a server that provides various services, such as a background server that processes data displayed on the terminal devices 101, 102, and 103. The background server may analyze and process the received data, and may feed back the processing results (e.g., recognition results) to the terminal device.

[0033] It should be noted that a server can be either hardware or software. When a server is hardware, it can be implemented as a distributed server cluster consisting of multiple servers, or as a single server. When a server is software, it can be implemented as multiple software programs or software modules (for example, multiple software programs or software modules used to provide distributed services), or as a single software program or software module. This is not specifically limited here.

[0034] It should be understood that Figure 1 The number of terminal devices, networks, and servers in the above description is merely illustrative. Any number of terminal devices, networks, and servers may be used as needed. In particular, if target data does not need to be acquired remotely, the above system architecture may not include a network, but may instead include only terminal devices or servers.

[0035] This embodiment discloses an agricultural teaching method based on virtual reality technology, which is applied to a server. Figure 2This is a flow chart of an agricultural teaching method based on virtual reality technology disclosed in an embodiment of the present application. Figure 2 As shown, the method includes the following steps: S201, generating a dynamic virtual scene based on three-dimensional geographic information data and a plant morphological feature library, wherein the dynamic virtual scene includes a target object and a growth environment of the target object; Specifically, the three-dimensional geographic information data includes terrain elevation, slope, aspect, terrain curvature data, surface undulation type and surface cover type. Among them, terrain elevation data is collected by drones or satellites, and slope, aspect and curvature parameters are generated by the terrain analysis toolkit of GIS software. The surface cover type is finely classified by combining multispectral remote sensing images and field sampling verification. Then, by integrating terrain elevation, soil properties obtained by remote sensing inversion and field sampling, climate layers generated by meteorological stations and reanalysis models, river networks and groundwater dynamics simulated by hydrological models, and aligning them to a unified geographic coordinate system through GIS (Geographic Information System) tools, a three-dimensional base with centimeter-level accuracy is formed, and NDVI (Normalized Difference Vegetation Index) is superimposed. The Normalized Difference Vegetation Index (NDVI) and field community survey data are used to construct an ecological framework with spatiotemporal continuity. The plant morphological feature library, based on botanical databases, 3D laser scanning, and literature parameters, establishes a digital parameter set covering organ geometry models, phenological development rules, and physiological response mechanisms. Dynamic virtual scene generation uses programmatic modeling to map plant parameters to the terrain base, driving individual spatial self-organization based on niche theory and competition algorithms. The dynamic growth engine connects to weather API (Application Programming Interface) data in real time, coupling environmental factors with physiological models (such as insufficient light causing stem elongation) to drive the evolution of organ morphology and phenological stages. The environmental system combines fluid simulation and the material point method to calculate the mechanical response of wind fields to tree canopies, the impact of precipitation on soil erosion, and the diffusion of water vapor due to transpiration. Ultimately, the game engine's deferred rendering pipeline and subsurface scattering technology create an interactive dynamic virtual scene.

[0036] Optionally, the generating of a dynamic virtual scene based on the three-dimensional geographic information data and the plant morphological feature library includes: Acquiring the three-dimensional geographic information data, including terrain elevation, slope, aspect, terrain curvature data, surface relief type, and surface cover type; Based on the type of the target object, calling the species-specific model in the plant morphological feature library to generate a distribution model of the target object, the distribution model including geometric structure parameters, texture characteristics and root distribution of the target object organ; The three-dimensional geographic information data is integrated with the distribution model to generate the dynamic virtual scene.

[0037] Specifically, in this embodiment, remote sensing mapping is used to acquire three-dimensional geographic information data of the target area, including terrain elevation, slope, aspect, curvature, surface relief type (e.g., mountains, hills, plains), and land cover type (e.g., vegetation, bare soil, water). Terrain elevation data is collected using drone LiDAR or satellite DEM, while slope, aspect, and curvature parameters are generated using a terrain analysis toolkit within GIS software. Land cover type is refined and classified using a combination of multispectral remote sensing imagery and field sampling.

[0038] Furthermore, based on the biological classification of the target plant species, the system dynamically invokes a pre-built library of plant morphological features through taxonomic mapping. Species-specific models are first matched according to the hierarchical structure of kingdom, phylum, class, order, family, genus, and species. In case of an inexact match, higher-level default parameters are inherited upwards. Organ geometry parameter rules: leaves use fractal dimension to control venation complexity and overlay Perlin noise textures. Stems incorporate mechanical properties to simulate gravitational bending. The root system uses the L-System (Lindenmayer System) algorithm to generate a primary and lateral root topology network, whose branching frequency is dynamically correlated with soil moisture. The spatial distribution model selects suitable areas through GIS niche analysis. A cellular automaton iterative competition algorithm, incorporating light, water, and spatial exclusion rules, simulates a dynamic succession process from rapid occupation by pioneer species to slow renewal by later species. A forest gap mechanism is also introduced to trigger secondary succession. The environmental coupling module injects real-time weather API data to drive phenological phase transitions. Sensitivity analysis verifies the model's robustness. Morphological feedback mechanisms respond to stresses (e.g., strong winds increase stem thickness and drought adjusts biomass allocation). Ultimately, subsurface scattering and LOD (Level of Detail) detail control are achieved through multi-scale rendering technology, supporting users to interactively adjust parameters to observe real-time ecological responses, and forming a distribution model for dynamic predictions from organs to communities.

[0039] Furthermore, the 3D geographic information data is spatially integrated with the distribution model. Using the Unity (3D engine) spatial registration interface, the plant model is aligned with the geographic data coordinate system, and a terrain-vegetation coupling algorithm is employed to achieve dynamic interaction. For example, the root model adaptively adjusts its extension direction based on terrain curvature data, while the canopy model uses geometric mapping technology to match the surface undulations. Simultaneously, linked lighting parameters drive real-time shadow rendering, ultimately resulting in a dynamic virtual scene containing the target object and its growing environment.

[0040] Optionally, the step of fusing the three-dimensional geographic information data with the distribution model to generate the dynamic virtual scene further includes: adjusting the distribution model according to the slope aspect, and matching the canopy morphology of the target object with the surface undulation type through geometric mapping technology to obtain a topological structure map, wherein the canopy morphology refers to the three-dimensional structural characteristics formed by the above-ground part of the plant; Retrieving a preset nutrient absorption efficiency database based on the surface cover type to generate input parameters for nutrient uptake of the target object; Dynamically correcting the growth direction vector of the target organ according to the terrain curvature data; The topological structure diagram, the input parameters and the growth direction vector are coupled with the terrain elevation through a three-dimensional engine for rendering to generate the dynamic virtual scene.

[0041] Specifically, the geographic illumination direction is calculated based on the target area's aspect data. For example, if the slope aspect is southeast (135° azimuth), the sun's projection angle is dynamically adjusted based on longitude, latitude, and time parameters to ensure that the canopy's primary axis aligns with the direction of sunlight received by the slope. Subsequently, a vertex displacement algorithm, part of geometric mapping technology, is used to dynamically bind the vertex coordinates of the canopy's 3D mesh to the surface relief data. Specifically, in steep slopes (slopes > 30°), a slope threshold triggers vertex displacement: lateral vertices are compressed proportionally to the slope value, reducing the canopy's lateral extension, while longitudinal vertices are raised along the terrain normal to prevent the canopy from intersecting the slope. This process is implemented using a vertex shader script written in a real-time rendering engine, for example, using a world position offset node. Slope data and vertex coordinates are input into a displacement function to drive the adaptive deformation of the canopy morphology. The resulting topology precisely matches the surface relief.

[0042] Furthermore, based on the surface cover type, the nitrogen, phosphorus, and potassium absorption coefficients for the corresponding soil types are retrieved from a preset nutrient absorption efficiency database to form a set of standardized transfer rates. For example, the nitrogen absorption coefficient in clay may be 0.8, 0.3 in sandy soil, and 0.9 in humus. At the same time, root density data of the target object in three-dimensional space is extracted based on the plant root distribution model to characterize the root distribution intensity at different soil depths. For example, root density is higher in the surface soil and decreases with depth. Subsequently, weighting factors are defined for soil absorption capacity and root density. For example, the weighting factor for soil type is set to 0.6, and the weighting factor for root density is set to 0.4, indicating that the inherent absorption characteristics of the soil have a greater impact on nutrient uptake. The weighting factors can be dynamically adjusted for different soil types. Next, a weighted calculation is performed: for each soil unit, the soil absorption coefficient and the root density at the corresponding location are linearly superimposed according to the weight. For example, if the nitrogen absorption coefficient in a cell is 0.8 and the root density is 0.7, the weighted nitrogen uptake parameter is 0.8 × 0.6 + 0.7 × 0.4 = 0.76. This is then applied simultaneously to phosphorus and potassium, ultimately generating an input parameter matrix that encompasses the comprehensive uptake capacity of multiple nutrients. Finally, this input parameter matrix is fed back into the plant growth model to drive dynamic adjustments in organ growth rates.

[0043] Furthermore, GIS tools are used to perform curvature analysis on the elevation data of the target area, generating planar curvature (horizontal concave and convex features) and profile curvature (vertical curved shape) rasters, which are converted into gradient vector fields, with the gradient direction pointing to the curvature descending path. Subsequently, in areas of convex curvature, such as ridges, the root growth direction is weightedly fused by the biological characteristic direction and the gradient direction. The weight increases dynamically with the curvature value, so that the root growth direction preferentially extends along the gradient direction to enhance the anchoring force. If an obstacle is encountered, the path is adjusted through path search. In areas of concave curvature, the branch direction is corrected to the tangent plane through projection of the terrain surface normal to avoid collision with the terrain. At the same time, the physics engine is used to detect potential intersections and trigger the offset growth of side branches. Finally, the corrected direction vector is input into the 3D engine to drive organ deformation, such as root vertex displacement and branch skeleton rotation, and is fused with the terrain data for rendering.

[0044] Furthermore, the topological structure diagram, nutrient input parameters, growth direction vector and terrain elevation data are imported into a three-dimensional rendering engine, such as Unreal Engine, and coordinate alignment is achieved through the spatial registration interface; the growth direction vector is bound to the plant model skeleton node based on the vertex shader script to drive the root vertex displacement and branch skeleton rotation, so that its shape adapts to the terrain curvature; the nutrient parameters are input into the growth simulation algorithm to dynamically adjust the organ growth rate; the integrated physics engine simulates environmental interaction, such as wind deformation and collision detection; the terrain elevation and plant model are integrated through a real-time rendering pipeline, combined with lighting projection and shadow calculation, to generate a high-fidelity virtual scene that includes dynamic growth behavior and terrain coupling, and the matching accuracy of the shape and environment is verified by comparison with measured data.

[0045] S202. Dynamically simulate the life cycle changes of the target object through a plant growth dynamics algorithm, wherein the changes include the organ morphology evolution and physiological index changes of the target object.

[0046] Specifically, a plant growth dynamics algorithm analyzes ecological factors such as ambient temperature, light intensity, and soil moisture in real time. These factors are substituted into the photosynthetic rate equation to calculate daily carbon accumulation, which is then combined with respiratory expenditure to determine net growth energy. This energy is then distributed to various organs using parameterized geometric rules. Leaves expand according to the vein bifurcation algorithm (the main vein extension rate is negatively correlated with lateral vein density), stem diameter grows radially based on sugar storage (0.02 mm thicker for every gram of glucose accumulated), and root topology iteratively generates new lateral roots. Furthermore, a mapping relationship between physiological indicators and visualization features is established. Chlorophyll content is converted into leaf RGB values using the Beer-Lambert law (every 10 μg / cm² increase in chlorophyll content results in an 8% increase in green channel intensity). Sugar concentration gradients drive the intensity changes in the stalk surface normal map. Finally, by daily updating vertex coordinates, texture maps, and material parameters, the morphological gradients, seasonal color changes, and lifecycle changes in structural self-organization of plant organs are realized in the virtual scene.

[0047] Optionally, the dynamically simulating the lifecycle changes of the target object further includes: determining a first developmental stage of an organ of the target object according to the type of the target object; Integrating the correlation parameters between the changes in the physiological indicators and the evolution of the organ morphology to establish a dynamic function between the carbon and nitrogen distribution ratio and the stem elongation rate of the target object; According to the dynamic function, the morphological change of the organ of the target object in the first developmental stage is driven.

[0048] Specifically, based on the biological classification of the target plant species, a pre-built plant morphological feature library is accessed to extract the species' developmental stage division rules, such as stage thresholds for seed germination, seedling, and vegetative growth. Based on species growth model parameters, such as accumulated temperature requirements, photoperiod sensitivity, or biomass accumulation thresholds, combined with the initial environmental data of the target area, the first developmental stage is dynamically divided through logical judgment or machine learning classifiers. The first developmental stage includes stages such as seed germination, seedling, and vegetative growth. For example, when the effective accumulated temperature is ≥200°Cd and the biomass is ≥5g, it is defined as the seedling stage. At the same time, stage priorities are set for different organs, such as the root system develops first during the germination period, and the stage parameters are bound to the skeleton nodes and texture materials of the three-dimensional model to ensure that the organ morphology matches the developmental stage. Finally, the accuracy of the stage division is calibrated in real time through environmental sensor data or meteorological API.

[0049] Furthermore, first, basic data were obtained through physiological experiments on target plant species, including the accumulation rate of photosynthetic products, nitrogen absorption efficiency, and daily stem elongation at different growth stages (such as seedling stage and vegetative growth period), to construct a correlation data set between the carbon and nitrogen distribution ratio (C:N ratio) and the stem elongation rate. For example, in a controlled environment experiment, when the C:N ratio was 10:1, the average daily stem elongation rate was measured to be 1.0 cm; when the C:N ratio was increased to 15:1, the rate decreased to 0.6 cm. Subsequently, a nonlinear regression model was used to fit the data to define the stem elongation rate. The relationship with the C:N ratio is: in, is the maximum theoretical elongation rate, is the half-saturation constant, is the response coefficient, is the lowest effective C:N ratio threshold, and the parameter is calibrated by the least square method (e.g. =8.2, =0.15). Environmental variables were further incorporated into the model as correction factors: when soil nitrogen concentration decreased by 20%, the minimum effective C:N ratio threshold was increased by 10% to reflect the inhibitory effect of nitrogen limitation on elongation. Finally, this dynamic function was integrated into a plant growth simulation engine, driving stem morphological changes through the skeleton nodes of the 3D model. The function's accuracy was verified using measured stem height data, ensuring that the dynamic coupling of carbon and nitrogen allocation and organ morphological evolution conformed to plant physiological laws.

[0050] Furthermore, the dynamic function is bound to the skeleton nodes of the three-dimensional model. Combined with the temperature, humidity, light intensity and soil nitrogen concentration data obtained in real time by environmental sensors, the stem elongation ΔL is iteratively calculated with a daily step size, and the function parameters are dynamically corrected. For example, the minimum effective C:N ratio threshold is adjusted when nitrogen is limited. Based on the L-system fractal rules or parameterized skeleton nodes, ΔL is converted into the geometric deformation of the three-dimensional model to drive the elongation of the stem internodes. The accumulation of photosynthetic products and nitrogen absorption processes are simulated simultaneously, and the C / N ratio is updated through a feedback mechanism to adjust the stem elongation rate in real time (for example, when the soil nitrogen concentration drops by 20%, the elongation decreases by 15%-20%). The biomass and effective accumulated temperature and other stage transition indicators are continuously monitored to trigger the recalibration of function parameters and the switching of organ priorities. The simulated stem height is compared with the measured data every day. If the error exceeds the threshold, the Bayesian optimization is automatically triggered to adjust the nonlinear term coefficient to ensure that the spatiotemporal dynamics of organ morphological evolution are consistent with physiological laws.

[0051] S203: Acquire a multimodal interaction signal, and generate a control instruction for the dynamic virtual scene according to the multimodal interaction signal.

[0052] Specifically, the acquisition and generation of multimodal interaction signals are achieved through signal collection using a depth camera (capturing the spatial coordinates of gestures), a bone conduction microphone (recognizing voice commands), a pressure sensor (sensing tactile force) and an eye tracker (tracking gaze points); the system uses Kalman filtering to fuse multi-source spatiotemporal data, and maps spatial gesture signals, voice commands, gaze points and tactile force into operation instructions through preset priority weights.

[0053] Optionally, the acquiring of the multimodal interaction signal and generating a control instruction for the dynamic virtual scene according to the multimodal interaction signal further comprises: Acquiring a spatial gesture signal, and parsing the spatial gesture signal into an adjustment instruction for the target organ of the target object and the growth environment; Recognizing semantic features in the voice command, and mapping the semantic features into parameters of the growth environment and adjustment values of the target organ; Locating a gaze point through eye tracking, and generating a dynamic monitoring request for changes in the physiological indicators of a target area of the target object according to the gaze point; Acquiring pressure sensing data from a force feedback device, and generating a physical deformation adjustment instruction for the target organ according to the pressure sensing data; The adjustment instruction, the adjustment value, the dynamic monitoring request and the physical deformation adjustment instruction are integrated to generate the control instruction.

[0054] Specifically, the user's gestures are captured in real time through a depth camera, and the OpenPose (open-source pose estimation tool) framework is used for gesture key-point detection and tracking. A pre-defined gesture semantic library is established, such as using both hands to scale the size of an organ or using a single finger to swipe to adjust the light intensity. The CNN (Convolutional Neural Network) classifier or the dynamic time warping algorithm is used to match the gesture trajectory to the pre-defined operation to generate adjustment instructions, such as the stem diameter +10% or the soil humidity -5%.

[0055] Furthermore, voice is obtained through a bone conduction microphone, and then converted into text through voice recognition. After that, semantic features are extracted through a BERT-based (Bidirectional Encoder Representations from Transformers) intent classification model, such as "adjust the temperature to 28°C" or "increase the leaf nitrogen content". A domain dictionary and a rule engine are constructed to map the semantics to environmental parameters or organ adjustment values, supporting fuzzy matching. For example, "grow faster" is mapped to the growth rate +15%. The input dialect (Mandarin / Cantonese / Wu dialect, etc.) is classified in real time by superimposing MFCC (Mel Frequency Cepstral Coefficients) and CNN, and the ASR model dynamically loaded based on Wav2Vec2.0 (self-supervised speech representation learning framework) and fine-tuned with more than 500 plant domain dialect instructions is used; a dialect and Mandarin comparison dictionary is constructed, such as the literal translation mapping of "nitrogen content" in Cantonese and the association of "temperature pair" in Wu dialect with "temperature", and the edit distance algorithm is combined to achieve fuzzy instruction matching; the BERT model is fine-tuned on dialect texts for intent classification, and when the confidence level is lower than 90%, candidate resolutions are popped up for the user to confirm again through eye movement or voice; the LSTM (Long Short-Term Memory Network) analyzes the user's dialect usage frequency to adjust the ASR (Automatic Speech Recognition) weight, and a crowdsourcing entry is opened to collect new dialect instructions, such as "thicken the stem" in Hakka dialect. After review, the dictionary is automatically updated and the model incremental training is triggered to achieve accurate parsing and continuous optimization of multi-dialect interaction.

[0056] Furthermore, the user's fixation points are captured in real time using an eye tracker. Through the ray casting method of the screen space coordinates and the three-dimensional scene coordinate system, the fixation points are located on the target organs of the virtual plant. When the fixation point stays for more than 2 seconds, the monitoring request for the physiological indicators in this area is automatically triggered, and the nutrient transport model or the water conduction algorithm is called to calculate parameters such as the local nitrogen content and the photosynthesis rate, and the dynamic changes are displayed in real time through a heat map or a line chart superimposed on the interface, supporting the user to switch the monitoring indicators through eye rotation, such as switching from nitrogen content to transpiration rate, to achieve fixation-driven dynamic physiological state tracking.

[0057] Furthermore, a force feedback device reads 3D pressure sensor data in real time (50Hz frequency, range 0-10N). After Kalman filtering and denoising, the pressure values are converted into organ deformation parameters using piecewise linear mapping. For example, 0-5N corresponds to 0-15° stem bending, and 5-10N triggers leaf curling. Combined with a finite element model to simulate force distribution, the displacement of 3D mesh vertices is dynamically calculated (displacement = pressure value × 0.02mm / N), triggering collision detection to prevent penetration. The haptic rendering engine is simultaneously invoked to calculate reaction forces based on the organ's material stiffness. Resistance is applied via the device's motor to simulate real-world touch. After pressure is released, a spring-mass model is activated to drive the organ back to its initial shape. Ultimately, physical deformation adjustment instructions are generated, including vertex coordinate updates, collision status, and haptic feedback parameters.

[0058] Furthermore, a standardized instruction data structure is first defined, encompassing organ displacement, environmental adjustment, monitoring request, physical deformation, target object identifier, parameter value, timestamp, and priority weight. For example, physical deformation instructions take precedence over gesture operations. A multimodal signal parsing module generates a raw instruction set in real time and encapsulates it into a structured data packet. Subsequently, priority queues and conflict resolution rules are used to logically integrate the instructions. For example, "physical deformation instructions prioritize gesture displacement" and "consecutive operations on the same organ are sorted by timestamp." If a command conflict is detected, such as a voice command requesting a pause in growth while a gesture continues to drag, a user confirmation prompt is triggered or a preset safety policy is executed. Ultimately, the action instruction is obtained.

[0059] S204, adjusting the environmental parameters in the growth environment and the target object according to the control instruction to obtain a dynamic simulation result; Specifically, multimodal commands such as voice and gestures are parsed into standardized parameters. For example, "increase the temperature by 2°C" is converted to a temperature value of +2. Parameters such as temperature, humidity, and light intensity in the virtual environment are updated in real time through control algorithms. The plant physiological model responds synchronously to environmental changes, automatically calculating physiological indicators such as stem elongation rate and leaf stomatal aperture, and adjusting the geometric shape of organs. Finally, through the Unity engine's ECS (Entity Component System), the changes in environmental light and shadow are coupled with the evolution of plant morphology for rendering, resulting in dynamic simulation results.

[0060] Optionally, adjusting the environmental parameters in the growth environment and the target object according to the control instruction to obtain a dynamic simulation result further includes: parsing the adjustment value in the control instruction and updating the multidimensional parameter set of the growth environment, the multidimensional parameter set including temperature gradient, humidity distribution, light intensity spectrum and soil moisture content; Calculating the physiological state of the target object based on the updated multidimensional parameter set using the organ-level physiological response model of the target object, the physiological state including stomatal conductance, transpiration rate, photosynthesis efficiency, and stress resistance factor; Establishing a dynamic mapping relationship between the variation of the multidimensional parameter set and the organ morphological parameter, and based on the dynamic mapping relationship, driving the target object organ to evolve in coordination with the physiological state; When any environmental parameter exceeds a first threshold, the morphological features of the target organ and the corresponding timestamp are recorded to generate an environmental stress response data set; The updated multi-dimensional parameter set is spatially aligned with the morphological features of the target organ to obtain the dynamic simulation result.

[0061] Specifically, control commands are semantically parsed using a predefined environmental parameter ontology library. A rule-based natural language matching mechanism combined with a contextual disambiguation algorithm is used to extract adjustment values for temperature gradients, humidity distribution, light intensity spectrum, and soil moisture content. Temperature gradient updates are performed using a global iterative calculation of the discretized heat conduction equation. Humidity distribution simulates the advection process along the air flow direction using a humidity diffusion model. The light intensity spectrum adjusts the light energy distribution within specific wavelength ranges based on a spectral weighting function. Soil moisture content is simulated by infiltration using the Richards equation for soil water movement coupled with the root water absorption term, resulting in an updated multidimensional parameter set.

[0062] Furthermore, based on the updated multidimensional parameter set, an organ-level physiological response model was invoked. Stomatal conductance was calculated using a Jarvis-type multi-factor response surface model, incorporating the effects of ambient temperature and humidity, light intensity, and leaf water potential. Transpiration rate was simulated using the Penman-Monteith formula combined with stomatal conductance. Photosynthetic efficiency was achieved by coupling the Farquhar biochemical model with a dynamic correction coefficient for light energy utilization. Stress resistance was quantified based on a nonlinear relationship between stress protein synthesis rate and environmental stress intensity. Physiological state parameters were spatially distributed on a three-dimensional organ mesh using finite element analysis. The time dimension was transiently solved using the Runge-Kutta method with an adaptive step size to ensure spatiotemporal consistency of physiological responses.

[0063] Furthermore, a dynamic mapping library between environmental parameter variations and organ morphological parameters was established, including piecewise linear functions for stem elongation rate and temperature gradient, Fourier series fitting of leaf expansion angle and light intensity spectrum, and threshold response models for root branch density and soil moisture content. Parameter sensitivity analysis identified the dominant environmental factors, and an L-system-based organ topology evolution algorithm, combined with biomechanical models, was employed to calculate cell wall expansion forces and tissue deformation gradients, driving dynamic adjustments in organ morphology. The morphological evolution process was physically constrained by the law of conservation of mass and momentum balance equations, ensuring synergy between organ morphology and physiological state in terms of energy distribution and material flow.

[0064] Furthermore, when environmental parameters exceed preset thresholds, such as temperature > 45°C or soil moisture content < 5%, the system initiates stress response data collection, acquires the leaf curl index through structured light scanning, and simultaneously reconstructs the three-dimensional root morphology using MRI (magnetic resonance imaging) medical imaging (resolution 0.1 mm³). The original 1024-dimensional morphological features are reduced to 12-dimensional physiological-related features through Kernel PCA (Kernel Principal Component Analysis). A blockchain smart contract is used to generate a SHA-3 hash fingerprint and anchor it with a timestamp, ultimately creating a standardized stress response dataset containing morphological features, environmental parameters, and timestamps.

[0065] Furthermore, when the environmental parameters are updated, the system uses multi-scale spatial registration technology to achieve accurate mapping of the parameter field and the organ morphology. First, the discretized temperature field, humidity field, and illumination field are spatially downsampled and unified to the 0.1mm resolution of the organ surface point cloud. Then, the coherent point drift algorithm is used to perform non-rigid registration of the parameter field and the three-dimensional morphology of the target organ (such as leaves and roots). Through iterative optimization, the mean square error between the parameter grid and the organ surface is reduced to less than 0.5mm, and the rotation matrix is optimized using the quaternion method to ensure that the registration process converges within 40 iterations. Finally, the environmental parameters are smoothly interpolated to the organ surface through the compactly supported radial basis function to generate a four-dimensional dynamic simulation result containing spatiotemporal information.

[0066] S205 , rendering the dynamic simulation results in real time through a three-dimensional visualization engine to generate an interactive interface for the target object.

[0067] Specifically, the 3D visualization engine processes dynamic simulation data in real time through an efficient rendering architecture, maps plant physiological indicators into organ color gradients and morphological animations, synchronously simulates environmental dynamics, combines a multimodal interactive interface, and uses LOD (Level of Detail) hierarchical rendering and virtualized geometry technology to optimize performance and output an interactive interface.

[0068] Optionally, generating an interactive interface for the target object further includes: Mapping the environmental parameters of the growth environment into a three-dimensional thermal map, and encoding the physiological indicators of the target object into an organ-level color scale map; Determining the spatial coordinates of the organs of the target object by a ray casting algorithm, associating the spatial coordinates of the organs with physiological parameters and a historical growth database, and generating organ-level data visualization labels; When the environmental parameter exceeds a second threshold, generating a dynamic control strategy based on a plant stress resistance model, the dynamic control strategy including a light environment adjustment parameter and a microclimate control scheme; The three-dimensional thermal map, the organ-level data visualization label and the dynamic control strategy are spatially aligned to generate the interactive interface.

[0069] Specifically, growth environment parameters are converted into continuous three-dimensional thermal field data using the inverse distance weighted method. Within the 3D engine, color mapping rules are defined based on the parameter value range (e.g., low to high temperatures correspond to blue to red). Using vertex shaders or volume rendering techniques, the thermal field data is mapped into a three-dimensional thermal layer (e.g., the temperature field is displayed as a gradient spherical cloud or isothermal surface). GPU instancing technology is used to optimize rendering performance and ensure real-time updates of the thermal layer in complex scenes.

[0070] Furthermore, differentiated coloring rules were established based on organ type. For example, leaf photosynthetic rate is represented using a segmented color scale (<5 μmol / m²s in red, 5-20 μmol in a linear gradient of yellow-green, and >20 μmol in dark green). Stomatal conductance is overlaid with transparency, with conductance values of 0-1 corresponding to 0-100% transparency. Stem lignification is mapped using grayscale values, with 0-255 corresponding to 0%-100% lignification. Root water uptake rate is encoded using a heat map (blue for low rates to red for high rates), with overlaid flow arrows indicating the direction of water transfer. All physiological indicator data are visualized with submillimeter precision through UV mapping of organ surfaces.

[0071] Furthermore, when interacting with a mouse or touch device, a ray is emitted from the camera viewport, and Unity is used to detect the collision point with the target organ model, obtaining the instance ID and spatial coordinates (x, y, z) of the colliding organ. Based on the organ ID, its physiological parameters and historical growth data, such as the stem length change curve over the past 24 hours, are retrieved from the database. A UI component is instantiated at this 3D spatial coordinate, dynamically displaying the label content (e.g., "Leaf ID: L001 | Photosynthetic Efficiency: 0.85 | Historical Peak: 0.92"). The label position is offset in screen space (e.g., 50 pixels upward from the camera's perspective) to avoid overlap with the model, and the anchor point is adjusted in real time as the viewing angle changes.

[0072] Furthermore, a second threshold for environmental parameters is set, such as temperature > 45°C or soil moisture < 10%, to monitor in real time whether these parameters exceed the limit. When these thresholds are exceeded, the plant stress tolerance model is invoked, inputting the current environmental parameters and physiological state, and outputting dynamic control strategies. For example, light environment adjustment can calculate the required light intensity reduction (e.g., from 1000 lux to 600 lux) or spectral adjustment (e.g., increasing blue light to inhibit excessive growth); microclimate control strategies can generate a spray cooling frequency (e.g., spray for 5 seconds every 10 minutes) or a ventilation rate (e.g., increasing wind speed from 0.5 m / s to 2 m / s). These control strategies are converted into device control instructions and sent via an IoT interface to environmental control devices, such as smart fill lights and misting systems. The effects of these strategies are simulated in a 3D scene, such as the color gradient update of the temperature field after cooling. The spray or airflow effects can be visualized using particle systems, such as Unity's VFX Graph.

[0073] Furthermore, the coordinate systems of the three-dimensional thermal layer, organ data labels, and control strategy prompt boxes are aligned to the scene's world coordinate system, and the layer rendering order is ensured through depth buffer management. For example, the thermal layer is placed below the organ model, and the label is always on top. When clicking on a specific area of the thermal layer, the environmental parameter curve of the area, such as a temperature time series line graph, is highlighted; when hovering over an organ label, a detailed historical data panel, such as a pop-up UI with charts and statistical summaries, is displayed; when the control strategy is triggered, a floating prompt box is generated at the edge of the scene for manual confirmation or adjustment of the strategy parameters. Detail level technology is used to dynamically simplify the rendering accuracy of the thermal layer and label according to the viewing distance, such as only displaying basic color blocks for distant organs; an asynchronous loading mechanism is used to batch process data requests to avoid interface freezes.

[0074] This embodiment also discloses an agricultural education system based on virtual reality technology. Figure 3 This is a module diagram of an agricultural education system based on virtual reality technology disclosed in an embodiment of the present application. Figure 3 As shown, the system includes: A scene generation module 301 is used to generate a dynamic virtual scene based on three-dimensional geographic information data and a plant morphological feature library, wherein the dynamic virtual scene includes a target object and a growth environment of the target object; An evolution module 302 is used to dynamically simulate the life cycle changes of the target object using a plant growth dynamics algorithm, wherein the changes include the organ morphology evolution and physiological index changes of the target object; An instruction generation module 303 is configured to obtain a multimodal interaction signal and generate a control instruction for the dynamic virtual scene according to the multimodal interaction signal; A dynamic simulation module 304 is configured to adjust environmental parameters in the growth environment and the target object according to the control instruction to obtain a dynamic simulation result; The visualization module 305 is used to render the dynamic simulation results in real time through a three-dimensional visualization engine to generate an interactive interface for the target object.

[0075] Optionally, the scene generation module 301 is specifically configured to: Acquiring the three-dimensional geographic information data, including terrain elevation, slope, aspect, terrain curvature data, surface relief type, and surface cover type; Based on the type of the target object, calling the species-specific model in the plant morphological feature library to generate a distribution model of the target object, the distribution model including geometric structure parameters, texture characteristics and root distribution of the target object organ; The three-dimensional geographic information data is integrated with the distribution model to generate the dynamic virtual scene.

[0076] Optionally, the scene generation module 301 is specifically configured to: adjusting the distribution model according to the slope aspect, and matching the canopy morphology of the target object with the surface undulation type through geometric mapping technology to obtain a topological structure map, wherein the canopy morphology refers to the three-dimensional structural characteristics formed by the above-ground part of the plant; Retrieving a preset nutrient absorption efficiency database based on the surface cover type to generate input parameters for nutrient uptake of the target object; Dynamically correcting the growth direction vector of the target organ according to the terrain curvature data; The topological structure diagram, the input parameters and the growth direction vector are coupled with the terrain elevation through a three-dimensional engine for rendering to generate the dynamic virtual scene.

[0077] Optionally, the evolution module 302 is specifically configured to: determining a first developmental stage of an organ of the target object according to the type of the target object; Integrating the correlation parameters between the changes in the physiological indicators and the evolution of the organ morphology to establish a dynamic function between the carbon and nitrogen distribution ratio and the stem elongation rate of the target object; According to the dynamic function, the morphological change of the organ of the target object in the first developmental stage is driven.

[0078] Optionally, the instruction generation module 303 is specifically configured to: Acquiring a spatial gesture signal, and parsing the spatial gesture signal into an adjustment instruction for the target organ of the target object and the growth environment; Recognizing semantic features in the voice command, and mapping the semantic features into parameters of the growth environment and adjustment values of the target organ; Locating a gaze point through eye tracking, and generating a dynamic monitoring request for changes in the physiological indicators of a target area of the target object according to the gaze point; Acquiring pressure sensing data from a force feedback device, and generating a physical deformation adjustment instruction for the target organ according to the pressure sensing data; The adjustment instruction, the adjustment value, the dynamic monitoring request and the physical deformation adjustment instruction are integrated to generate the control instruction.

[0079] Optionally, the dynamic simulation module 304 is specifically configured to: parsing the adjustment value in the control instruction and updating the multidimensional parameter set of the growth environment, the multidimensional parameter set including temperature gradient, humidity distribution, light intensity spectrum and soil moisture content; Calculating the physiological state of the target object based on the updated multidimensional parameter set using the organ-level physiological response model of the target object, the physiological state including stomatal conductance, transpiration rate, photosynthesis efficiency, and stress resistance factor; Establishing a dynamic mapping relationship between the variation of the multidimensional parameter set and the organ morphological parameter, and based on the dynamic mapping relationship, driving the target object organ to evolve in coordination with the physiological state; When any environmental parameter exceeds a first threshold, the morphological features of the target organ and the corresponding timestamp are recorded to generate an environmental stress response data set; The updated multi-dimensional parameter set is spatially aligned with the morphological features of the target organ to obtain the dynamic simulation result.

[0080] Optionally, the visualization module 305 is specifically configured to: Mapping the environmental parameters of the growth environment into a three-dimensional thermal map, and encoding the physiological indicators of the target object into an organ-level color scale map; Determining the spatial coordinates of the organs of the target object by a ray casting algorithm, associating the spatial coordinates of the organs with physiological parameters and a historical growth database, and generating organ-level data visualization labels; When the environmental parameter exceeds a second threshold, generating a dynamic control strategy based on a plant stress resistance model, the dynamic control strategy including a light environment adjustment parameter and a microclimate control scheme; The three-dimensional thermal map, the organ-level data visualization label and the dynamic control strategy are spatially aligned to generate the interactive interface.

[0081] It should be noted that the above embodiments provide devices that implement their functions using only the division of the above functional modules as examples. In actual applications, the above functions can be assigned to different functional modules as needed, that is, the internal structure of the device can be divided into different functional modules to complete all or part of the functions described above. In addition, the device and method embodiments provided in the above embodiments are based on the same concept. The specific implementation process is detailed in the method embodiment and will not be repeated here.

[0082] This embodiment also discloses an electronic device, referring to Figure 4 The electronic device may include: at least one processor 401 , at least one communication bus 402 , a user interface 403 , a network interface 404 , and at least one memory 405 .

[0083] The communication bus 402 is used to implement the connection and communication between these components.

[0084] The user interface 403 may include a display screen (Display) and a camera (Camera). Optionally, the user interface 403 may also include a standard wired interface and a wireless interface.

[0085] The network interface 404 may optionally include a standard wired interface or a wireless interface (such as a WI-FI interface).

[0086] Processor 401 may include one or more processing cores. Using various interfaces and circuits, processor 401 connects to various components within the server. It executes instructions, programs, code sets, or instruction sets stored in memory 405, as well as accesses data stored in memory 405, to perform various server functions and process data. Optionally, processor 401 may be implemented using at least one of the following hardware forms: a digital signal processing (DSP), a field-programmable gate array (FPGA), or a programmable logic array (PLA). Processor 401 may integrate one or a combination of a central processing unit (CPU), a graphics processing unit (GPU), and a modem. The CPU primarily processes the operating system, user interface, and application programs; the GPU is responsible for rendering and drawing content displayed on the display screen; and the modem handles wireless communications. It is understood that the modem may also be implemented independently of the processor 401 and implemented as a separate chip.

[0087] Among them, the memory 405 may include a random access memory (RAM) or a read-only memory (Read-Only Memory). Optionally, the memory 405 includes a non-transitory computer-readable storage medium. The memory 405 can be used to store instructions, programs, codes, code sets or instruction sets. The memory 405 may include a program storage area and a data storage area, wherein the program storage area may store instructions for implementing an operating system, instructions for at least one function (such as a touch function, a sound playback function, an image playback function, etc.), instructions for implementing the above-mentioned various method embodiments, etc.; the data storage area may store data involved in the above-mentioned various method embodiments, etc. The memory 405 may also be optionally at least one storage device located away from the aforementioned processor 401. As Figure 4 As shown, the memory 405 as a computer storage medium may include an operating system, a network communication module, a user interface module, and an application program for an agricultural teaching method based on virtual reality technology.

[0088] exist Figure 4 In the electronic device shown, the user interface 403 is mainly used to provide an input interface for the user and obtain data input by the user; and the processor 401 can be used to call an application program stored in the memory 405 for an agricultural teaching method based on virtual reality technology. When executed by one or more processors 401, the electronic device executes one or more methods in the above embodiments.

[0089] It should be noted that for the aforementioned method embodiments, for simplicity of description, they are all expressed as a series of action combinations, but those skilled in the art should be aware that this application is not limited by the order of the actions described, because according to this application, certain steps can be performed in other orders or simultaneously. Secondly, those skilled in the art should also be aware that the embodiments described in the specification are all preferred embodiments, and the actions and modules involved are not necessarily required for this application.

[0090] In the above embodiments, the description of each embodiment has its own focus. For parts that are not described in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0091] In the several embodiments provided in this application, it should be understood that the disclosed devices can be implemented in other ways. For example, the device embodiments described above are merely schematic, such as the division of units, which is only a logical function division. In actual implementation, there may be other division methods, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some service interface, and the indirect coupling or communication connection of devices or units can be electrical or other forms.

[0092] Units described as separate components may or may not be physically separate, and components shown as units may or may not be physical units, that is, they may be located in one place or distributed across multiple network units. Some or all of these units may be selected to achieve the purpose of this embodiment according to actual needs.

[0093] In addition, the functional units in the various embodiments of the present application may be integrated into a single processing unit, or each unit may exist physically separately, or two or more units may be integrated into a single unit. The aforementioned integrated units may be implemented in the form of hardware or software functional units.

[0094] If the integrated unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable memory. Based on this understanding, the technical solution of this application, or the portion that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a memory 405 and includes several instructions for causing a computer device (which can be a personal computer, server, or network device, etc.) to execute all or part of the steps of the various embodiments of the method of this application. The aforementioned memory 405 includes various media that can store program code, such as a USB flash drive, a mobile hard drive, a magnetic disk, or an optical disk.

[0095] The above is only an exemplary embodiment of the present disclosure and cannot be used to limit the scope of the present disclosure. That is, any equivalent changes and modifications made according to the teachings of the present disclosure are still within the scope of the present disclosure. After considering the disclosure of the specification, those skilled in the art will easily think of other embodiments of the present disclosure. This application is intended to cover any variations, uses or adaptive changes of the present disclosure, which follow the general principles of the present disclosure and include common knowledge or customary technical means in the technical field that are not recorded in the present disclosure. The description and examples are to be regarded as exemplary only, and the scope and spirit of the present disclosure are defined by the claims.

Claims

1. An agricultural teaching method based on virtual reality technology, characterized in that: Applied to a server, the method includes: Generate a dynamic virtual scene based on three-dimensional geographic information data and a plant morphological feature library, wherein the dynamic virtual scene includes a target object and a growth environment of the target object; Dynamically simulate the life cycle changes of the target object through a plant growth dynamics algorithm, wherein the changes include the organ morphological evolution and physiological index changes of the target object; Acquiring a multimodal interaction signal, and generating a control instruction for the dynamic virtual scene according to the multimodal interaction signal; Adjusting environmental parameters in the growth environment and the target object according to the control instruction to obtain a dynamic simulation result; The dynamic simulation results are rendered in real time through a three-dimensional visualization engine to generate an interactive interface for the target object.

2. The method according to claim 1, characterized in that The generating of a dynamic virtual scene based on the three-dimensional geographic information data and the plant morphological feature library includes: Acquiring the three-dimensional geographic information data, including terrain elevation, slope, aspect, terrain curvature data, surface relief type, and surface cover type; Based on the type of the target object, calling the species-specific model in the plant morphological feature library to generate a distribution model of the target object, the distribution model including geometric structure parameters, texture characteristics and root distribution of the target object organ; The three-dimensional geographic information data is integrated with the distribution model to generate the dynamic virtual scene.

3. The method according to claim 2, characterized in that The fusing of the three-dimensional geographic information data with the distribution model to generate the dynamic virtual scene further comprises: adjusting the distribution model according to the slope aspect, and matching the canopy morphology of the target object with the surface undulation type through geometric mapping technology to obtain a topological structure map, wherein the canopy morphology refers to the three-dimensional structural characteristics formed by the above-ground part of the plant; Retrieving a preset nutrient absorption efficiency database based on the surface cover type to generate input parameters for nutrient uptake of the target object; Dynamically correcting the growth direction vector of the target organ according to the terrain curvature data; The topological structure diagram, the input parameters and the growth direction vector are coupled with the terrain elevation through a three-dimensional engine for rendering to generate the dynamic virtual scene.

4. The method according to claim 1, wherein The dynamically simulating the life cycle change of the target object further includes: determining a first developmental stage of an organ of the target object according to the type of the target object; Integrating the correlation parameters between the changes in the physiological indicators and the evolution of the organ morphology to establish a dynamic function between the carbon and nitrogen distribution ratio and the stem elongation rate of the target object; According to the dynamic function, the morphological change of the organ of the target object in the first developmental stage is driven.

5. The method according to claim 1, wherein The acquiring of the multimodal interaction signal and generating a control instruction for the dynamic virtual scene according to the multimodal interaction signal further includes: Acquiring a spatial gesture signal, and parsing the spatial gesture signal into an adjustment instruction for the target organ of the target object and the growth environment; Recognizing semantic features in the voice command, and mapping the semantic features into parameters of the growth environment and adjustment values of the target organ; Locating a gaze point through eye tracking, and generating a dynamic monitoring request for changes in the physiological indicators of a target area of the target object according to the gaze point; Acquiring pressure sensing data from a force feedback device, and generating a physical deformation adjustment instruction for the target organ according to the pressure sensing data; The adjustment instruction, the adjustment value, the dynamic monitoring request and the physical deformation adjustment instruction are integrated to generate the control instruction.

6. The method according to claim 1, characterized in that The adjusting the environmental parameters in the growth environment and the target object according to the control instruction to obtain a dynamic simulation result further includes: parsing the adjustment value in the control instruction and updating the multidimensional parameter set of the growth environment, the multidimensional parameter set including temperature gradient, humidity distribution, light intensity spectrum and soil moisture content; Calculating the physiological state of the target object based on the updated multidimensional parameter set using the organ-level physiological response model of the target object, the physiological state including stomatal conductance, transpiration rate, photosynthesis efficiency, and stress resistance factor; Establishing a dynamic mapping relationship between the variation of the multidimensional parameter set and the organ morphological parameter, and based on the dynamic mapping relationship, driving the target object organ to evolve in coordination with the physiological state; When any environmental parameter exceeds a first threshold, the morphological features of the target organ and the corresponding timestamp are recorded to generate an environmental stress response data set; The updated multi-dimensional parameter set is spatially aligned with the morphological features of the target organ to obtain the dynamic simulation result.

7. The method according to claim 1, characterized in that Generating an interactive interface for the target object further includes: Mapping the environmental parameters of the growth environment into a three-dimensional thermal map, and encoding the physiological indicators of the target object into an organ-level color scale map; Determining the spatial coordinates of the organs of the target object by a ray casting algorithm, associating the spatial coordinates of the organs with physiological parameters and a historical growth database, and generating organ-level data visualization labels; When the environmental parameter exceeds a second threshold, a dynamic control strategy is generated based on a plant stress resistance model, wherein the dynamic control strategy includes a light environment adjustment parameter and a microclimate control scheme; The three-dimensional thermal map, the organ-level data visualization label and the dynamic control strategy are spatially aligned to generate the interactive interface.

8. An agricultural teaching system based on virtual reality technology, characterized in that: Specifically include: A scene generation module, configured to generate a dynamic virtual scene based on three-dimensional geographic information data and a plant morphological feature library, wherein the dynamic virtual scene includes a target object and a growth environment of the target object; An evolution module, configured to dynamically simulate the life cycle changes of the target object through a plant growth dynamics algorithm, wherein the changes include the organ morphology evolution and physiological index changes of the target object; An instruction generation module, configured to obtain a multimodal interaction signal and generate a control instruction for the dynamic virtual scene according to the multimodal interaction signal; A dynamic simulation module, configured to adjust environmental parameters in the growth environment and the target object according to the control instruction to obtain a dynamic simulation result; The visualization module is used to render the dynamic simulation results in real time through a three-dimensional visualization engine to generate an interactive interface for the target object.

9. An electronic device, characterized in that: The electronic device comprises a processor, a memory, a user interface and a network interface, wherein the memory is used to store instructions, the user interface and the network interface are both used to communicate with other devices, and the processor is used to execute the instructions stored in the memory so that the electronic device executes the method according to any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that The computer-readable storage medium stores instructions, and when the instructions are executed, the method according to any one of claims 1 to 7 is executed.

Images