Landscape garden planting planning management method and system based on terrain environment analysis

Abstract

The invention provides a landscape garden planting planning management method and system based on terrain environment analysis, and the method comprises the steps: generating a comprehensive terrain environment database through collecting comprehensive environment and biodiversity data; generating a plant ecological adaptability prediction model by using a genetic algorithm to generate an ecological adaptability intelligent evaluation result; obtaining a first target planting combination and a layout scheme through the constructed three-dimensional virtual ecological system model in combination with a user interactive function; optimizing in combination with a style migration algorithm and an emotion perception interactive design method to obtain a final target planting combination and layout scheme; monitoring key monitoring points and indexes to obtain existing planting ecological data, and performing landscape garden planting planning management based on the target planting combination and layout scheme and the existing planting ecological data; according to the invention, intelligentization, individuation and sustainability of landscape garden planting planning are realized, and powerful support is provided for design and management of landscape gardens.

Description

Technical Field

[0001] The embodiments of the present invention relate to the field of environmental science and ecological engineering technology, and in particular to a landscape gardening planting planning management method and system based on terrain environment analysis. Background Art

[0002] The planting planning and management of landscape gardening needs to comprehensively consider multiple environmental factors such as terrain, climate, soil type, etc. to ensure that plants can grow healthily and in harmony with the surrounding environment. In the process of modern urbanization, higher requirements are put forward for the effective use of limited space and the protection of the ecological environment.

[0003] At present, landscape planting planning mainly relies on the experience of designers and limited data analysis. Traditional empirical judgments are difficult to fully cover the complex natural environmental variables, which can easily lead to the selected plants not being adapted to the specific conditions of the area, affecting the long-term survival rate; traditional methods only rely on limited environmental data, which is incomplete and easily ignores the influence of other factors. Summary of the invention

[0004] The embodiment of the present invention provides a landscape planting planning management method and system based on terrain environment analysis, which is used to solve the problems in the prior art that it is difficult to fully cover complex natural environment variables, the data is incomplete, and the influence of other factors is easily ignored.

[0005] In a first aspect, an embodiment of the present invention provides a landscape gardening planting planning and management method based on terrain environment analysis, comprising: Collecting comprehensive environmental and biodiversity data to generate a comprehensive terrain environmental database, the comprehensive environmental and biodiversity data including surface images, historical meteorological data, soil type distribution maps, and biodiversity census information; Based on the comprehensive terrain environment database, a genetic algorithm is used to simulate the response differences of different plant genotypes under specific environmental conditions to generate a plant ecological adaptability prediction model, and based on the plant ecological adaptability prediction model, an ecological adaptability intelligent evaluation result is generated; Based on the ecological adaptability intelligent assessment result, a three-dimensional virtual ecosystem model is constructed using a generative adversarial network in deep learning to simulate the natural growth process of multiple plants in a selected area and the interaction between plants, and to generate an optimal planting combination and layout scheme to be optimized. The optimal planting combination and layout scheme to be optimized is optimized by combining user interactive functions and collaborative filtering algorithms to obtain a first target planting combination and layout scheme; Using a style transfer algorithm and an emotion-aware interactive design method, the aesthetic elements in the artwork and user preference feedback are integrated with the first target planting combination and layout scheme to obtain the final target planting combination and layout scheme; Based on the key monitoring points and indicators determined in the final target planting combination and layout plan, the ecological environment of the planted area is monitored to obtain the existing planting ecological data, and landscape planting planning and management are carried out based on the final target planting combination and layout plan and the existing planting ecological data.

[0006] Optionally, based on the ecological adaptability intelligent assessment result, a three-dimensional virtual ecosystem model is constructed using a generative adversarial network in deep learning to simulate the natural growth process of multiple plants in a selected area and the interaction between plants, and to generate an optimal planting combination and layout scheme to be optimized. The optimal planting combination and layout scheme to be optimized is optimized by combining a user interactive function and a collaborative filtering algorithm to obtain a first target planting combination and layout scheme, including: Based on the results of the intelligent assessment of ecological adaptability, basic ecological and environmental parameters and dynamic environmental variables are obtained, and the various parameters of the simulation engine of the virtual ecosystem are adjusted in combination with a multi-objective optimization algorithm to obtain a preliminary parameter configuration, and the preliminary parameter configuration is adjusted using Bayesian optimization technology to generate an optimal parameter configuration; Based on the optimal parameter configuration, a conditional generative adversarial network is used to construct a target virtual ecosystem model, and a self-attention mechanism is introduced during the construction process to improve the conditional generative adversarial network architecture to optimize the construction process; Based on the target virtual ecosystem model, the natural growth process of multiple plants in the selected area and the interaction between the plants are simulated to obtain a target simulation result. Based on the target simulation result, a reinforcement learning algorithm is used to quantitatively evaluate the effects of different plant combinations to search for the best planting combination. Analyze the spatial correlation between different plants in combination with graph neural network, predict the growth trend of different plants and the impact of different plant growth on the surrounding environment based on the spatial correlation, obtain plant growth prediction results, and generate the best planting combination and layout plan to be optimized based on the best planting combination and the plant growth prediction results; A user interactive function is introduced to make preliminary adjustments to the key parameters of the target virtual ecosystem model according to specific design requirements, so as to obtain the best planting combination and layout scheme of intermediate optimization, and a collaborative filtering algorithm is applied to obtain successful examples of landscape planting planning, so as to optimize the best planting combination and layout scheme of intermediate optimization based on the successful examples of landscape planting planning, and obtain the first target planting combination and layout scheme.

[0007] Optionally, based on the target virtual ecosystem model, the natural growth process of multiple plants in the selected area and the interaction between the plants are simulated to obtain a target simulation result. Based on the target simulation result, a reinforcement learning algorithm is used to quantitatively evaluate the effects of different plant combinations to search for the best planting combination, including: Based on the optimal parameter configuration set in the target virtual ecosystem model, the initial conditions and boundary conditions are defined, and plant individuals are initialized to simulate the natural growth process of multiple plants in the selected area and the interaction between plants, and obtain preliminary simulation results; Introducing dynamic environmental variables and real-time feedback mechanisms in the simulation process to adjust the optimal parameter configuration according to the growth conditions of the individual plants and changes in the growth environment to optimize the simulation process, wherein the dynamic environmental variables include seasonal climate fluctuations and the impact of emergencies; Introducing multi-physics field coupling simulation technology, simulating the effects of multiple physical phenomena on plant growth at the same time, obtaining physical simulation results, combining the preliminary simulation results with the physical simulation results, determining target simulation results, the target simulation results including key indicators and the performance of interactions between plants, the key indicators including plant growth rate, plant health index and reproductive success rate, and the physical phenomena including hydrological cycle, heat conduction and photosynthesis; Based on the target simulation results, a reinforcement learning algorithm is applied to quantitatively evaluate the effects of different plant combinations to generate an optimal planting combination suitable for the selected area.

[0008] Optionally, comprehensive environmental and biodiversity data are collected to generate a comprehensive terrain environment database, wherein the comprehensive environmental and biodiversity data includes surface images, meteorological historical data, soil type distribution maps, and biodiversity census information, including: Using multi-source heterogeneous data fusion technology to collect comprehensive environment and biodiversity data, pre-process the comprehensive environment and biodiversity data, and generate a multi-source data set; Applying generative adversarial networks and convolutional neural networks in deep learning to intelligently enhance the surface images and meteorological data in the multi-source dataset, generating images of missing areas of the multi-source dataset, and identifying and annotating key features in the multi-source dataset to generate an enhanced dataset, wherein the key features include vegetation coverage and land use type; Combining the time dimension and the space dimension in the enhanced data set by using a space-time cube model to generate a space-time evolution map to reflect the environmental dynamics in the selected area; Applying a graph neural network to analyze the correlation between different locations in the spatiotemporal evolution graph to identify target locations that have mutual influence within a specific time period, and predicting environmental evolution based on the target locations; A comprehensive terrain environment database is constructed based on the enhanced data set, the spatiotemporal evolution diagram and the environmental evolution situation.

[0009] Optionally, a space-time cube model is used to combine the time dimension and the space dimension in the enhanced data set to generate a space-time evolution diagram to reflect the environmental dynamics in the selected area, including: Based on the enhanced data set, combined with planning management objectives and data characteristics, determine the time granularity and spatial resolution of the space-time cube model; Based on the temporal granularity and spatial resolution, applying spatial indexing technology, indexing the enhanced comprehensive environment and biodiversity data in the enhanced data set to generate an optimized index structure; Based on the optimized index structure, the enhanced integrated environment and biodiversity data are mapped to corresponding spatiotemporal locations to generate a spatiotemporal cube model, and in the process of generating the spatiotemporal cube model, a spatiotemporal interpolation algorithm is used to add missing data points to optimize the spatiotemporal cube model; By combining the space-time cube model and the three-dimensional visualization engine, the environmental changes in the selected area are visualized to generate a space-time evolution diagram to reflect the environmental dynamics in the selected area.

[0010] Optionally, based on the comprehensive terrain environment database, a genetic algorithm is used to simulate the response differences of different plant genotypes under specific environmental conditions to generate a plant ecological adaptability prediction model, and based on the plant ecological adaptability prediction model, an ecological adaptability intelligent assessment result is generated, including: selecting target environmental variables and plant genotypes based on the comprehensive terrain environmental database; Based on the target environmental variables and plant genotypes, using a genetic algorithm to simulate the response differences of different plant genotypes under specific environmental conditions to generate a plant ecological adaptability prediction model to be optimized; Applying a reinforcement learning algorithm, defining a reward function by combining multiple evaluation indicators, evaluating the adaptability scores of different plant combinations based on the reward function, optimizing the plant ecological adaptability prediction model to be optimized based on the adaptability scores, and obtaining a plant ecological adaptability prediction model, wherein the evaluation indicators include plant growth rate, stress resistance, and aesthetic value; Based on the plant ecological adaptability prediction model, the interactions between different plants and the impacts of different plants on the ecosystem are predicted and analyzed to generate ecological adaptability intelligent evaluation results.

[0011] Optionally, a style transfer algorithm and an emotion-aware interactive design method are used to integrate the aesthetic elements in the artwork and the user preference feedback with the first target planting combination and layout scheme to obtain a final target planting combination and layout scheme, including: Using the style transfer algorithm in deep learning to extract aesthetic elements from artworks, the aesthetic elements include color palette, texture features, and spatial layout patterns; Collect user preference feedback using emotion-aware interaction design methods to obtain user preferences and emotional response information to different landscape elements. The emotion-aware interaction design methods include questionnaire surveys, focus group discussions, and eye-tracking experiments. A cross-domain transfer learning model is constructed to integrate the aesthetic elements, the preference and emotional response information, and the first target planting combination and layout plan to obtain a final target planting combination and layout plan.

[0012] In a second aspect, an embodiment of the present invention provides a landscape gardening planting planning and management system based on terrain environment analysis, comprising: A collection module, for collecting comprehensive environmental and biodiversity data to generate a comprehensive terrain environment database, wherein the comprehensive environmental and biodiversity data includes surface images, meteorological historical data, soil type distribution maps, and biodiversity census information; A simulation module, for simulating the response differences of different plant genotypes under specific environmental conditions using a genetic algorithm based on the comprehensive terrain environment database to generate a plant ecological adaptability prediction model, and generating an ecological adaptability intelligent evaluation result based on the plant ecological adaptability prediction model; A generation module is used to construct a three-dimensional virtual ecosystem model based on the ecological adaptability intelligent evaluation result by using a generative adversarial network in deep learning to simulate the natural growth process of multiple plants in a selected area and the interaction between plants, generate an optimal planting combination and layout scheme to be optimized, and optimize the optimal planting combination and layout scheme to be optimized by combining a user interactive function and a collaborative filtering algorithm to obtain a first target planting combination and layout scheme; An optimization module, for integrating the aesthetic elements in the artwork and the user preference feedback with the first target planting combination and layout scheme by using a style transfer algorithm and an emotion-aware interactive design method, to obtain a final target planting combination and layout scheme; A management module is used to monitor the ecological environment of the planted area based on the key monitoring points and indicators determined in the final target planting combination and layout plan, obtain the existing planting ecological data, and perform landscape planting planning management based on the final target planting combination and layout plan and the existing planting ecological data.

[0013] In a third aspect, an embodiment of the present invention provides a computing device, comprising a processor and a memory, wherein the memory stores a computer program, and the processor is configured to run the computer program to execute a landscape planting planning and management method based on terrain environment analysis as described in any one of the first aspects.

[0014] In a fourth aspect, an embodiment of the present invention provides a computer storage medium having computer program instructions stored thereon, wherein the computer program instructions, when executed by a processor, implement a landscape planting planning and management method based on terrain environment analysis as described in any one of the first aspects.

[0015] In an embodiment of the present invention, comprehensive environmental and biodiversity data are collected to generate a comprehensive terrain environment database, wherein the comprehensive environmental and biodiversity data include surface images, meteorological historical data, soil type distribution maps, and biodiversity census information; based on the comprehensive terrain environment database, a genetic algorithm is used to simulate the response differences of different plant genotypes under specific environmental conditions to generate a plant ecological adaptability prediction model; based on the plant ecological adaptability prediction model, an ecological adaptability intelligent evaluation result is generated; based on the ecological adaptability intelligent evaluation result, a three-dimensional virtual ecosystem model is constructed using a generative adversarial network in deep learning to simulate the natural growth process of multiple plants in a selected area and the interactions between plants. Function: generate the best planting combination and layout scheme to be optimized, combine the user interactive function and collaborative filtering algorithm to optimize the best planting combination and layout scheme to be optimized, and obtain the first target planting combination and layout scheme; adopt the style migration algorithm and the emotion perception interactive design method to integrate the aesthetic elements in the artwork and the user preference feedback with the first target planting combination and layout scheme to obtain the final target planting combination and layout scheme; based on the key monitoring points and indicators determined in the final target planting combination and layout scheme, monitor the ecological environment of the planted area to obtain the existing planting ecological data, and carry out landscape planting planning and management based on the final target planting combination and layout scheme and the existing planting ecological data. The technical solution provided by the present invention provides a solid foundation for subsequent precise simulation and evaluation through a comprehensive and integrated terrain environment database, ensuring the integrity and accuracy of the data, thereby improving the scientific nature of the overall planning; the ecological adaptability intelligent evaluation results can more accurately predict the growth of plants in the selected area and their interactions, improving the reliability and rationality of the planning; the target planting combination and layout scheme enable the present invention to not only have ecological benefits, but also provide good visual experience and usage functions; real-time monitoring is used to obtain existing planting ecological data, and continuous planting planning management is carried out based on this, ensuring long-term ecological benefits and sustainable development, while the planting scheme can be dynamically adjusted according to actual conditions, enhancing the flexibility and adaptability of the system. Among them, by defining initial conditions and boundary conditions, introducing dynamic environmental variables and real-time feedback mechanisms, applying multi-physics field coupling simulation technology to quantitative evaluation using reinforcement learning algorithms, the intelligentization and personalization of landscape planting planning are realized. This method not only improves the accuracy and reliability of the simulation, but also ensures the scientific nature and ecological benefits of the design scheme, and significantly improves the quality of planning and user experience. By accurately capturing the dynamic process of environmental changes and plant growth, the planting scheme is optimized, the harmonious development of the ecosystem is promoted, and strong support is provided for landscape design.

[0016] These and other aspects of the present invention will become more apparent from the following description of the embodiments. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0018] Figure 1 A flow chart of a landscape gardening planting planning and management method based on terrain environment analysis provided by an embodiment of the present invention; Figure 2 A structural schematic diagram of a landscape planting planning and management system based on terrain environment analysis provided by an embodiment of the present invention; Figure 3 A schematic diagram of the structure of a computing device provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0019] In order to enable those skilled in the art to better understand the solutions of the present invention, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the accompanying drawings in the embodiments of the present invention.

[0020] In some of the processes described in the specification and claims of the present invention and the above-mentioned figures, multiple operations that appear in a specific order are included, but it should be clearly understood that these operations may not be executed in the order in which they appear in this article or executed in parallel. The serial numbers of the operations, such as 101, 102, etc., are only used to distinguish different operations, and the serial numbers themselves do not represent any execution order. In addition, these processes may include more or fewer operations, and these operations may be executed in sequence or in parallel. It should be noted that the descriptions of "first", "second", etc. in this article are used to distinguish different messages, devices, modules, etc., do not represent the order of precedence, and do not limit the "first" and "second" to be different types.

[0021] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative work are within the scope of protection of the present invention.

[0022] Figure 1 A flow chart of a landscape gardening planting planning and management method based on terrain environment analysis is provided for an embodiment of the present invention, such as Figure 1 As shown, the method includes: In the face of the growing scientific and personalized needs in landscape planting planning, traditional methods have significant deficiencies in data comprehensiveness, ecological adaptability prediction, and user experience. In order to overcome these challenges, based on this, the present invention provides a landscape planting planning management method based on terrain environment analysis, such as Figure 1 ,include: Step 101: Collecting comprehensive environment and biodiversity data to generate a comprehensive terrain environment database, wherein the comprehensive environment and biodiversity data includes surface images, meteorological historical data, soil type distribution maps, and biodiversity census information; In this step, surface images refer to high-resolution images collected by satellite remote sensing, drone aerial photography, etc., which are used to analyze topography and vegetation coverage. Historical meteorological data refers to long-term records of temperature, precipitation, wind speed, sunshine duration, etc., which are used to evaluate the impact of climatic conditions on plant growth. Soil type distribution map refers to a map drawn through soil sampling and experimental analysis, showing information such as soil texture, fertility and pH value in different regions. Biodiversity census information refers to data obtained through literature research and analysis, covering the species of animals and plants in the region and their distribution.

[0023] For example, in a landscape project in a city park, surface images of the area, historical meteorological data from the past decade, soil type distribution maps, and detailed biodiversity census information were first collected. These data were integrated into a comprehensive terrain environment database, providing comprehensive basic information for subsequent ecological adaptability assessments. For example, through the analysis of surface images, the distribution of wetlands, grasslands, and woodlands in the park was determined; using historical meteorological data, the temperature and humidity changes in different seasons were evaluated; combined with soil type distribution maps, the best areas for the growth of different types of plants were identified; and biodiversity census information helped planners understand the distribution of existing species and avoid the introduction of alien invasive species.

[0024] Step 102: Based on the comprehensive terrain environment database, using a genetic algorithm to simulate the response differences of different plant genotypes under specific environmental conditions to generate a plant ecological adaptability prediction model, and based on the plant ecological adaptability prediction model, generating an ecological adaptability intelligent evaluation result; In this step, specific environmental conditions refer to the combination of various specific factors that affect plant growth and ecosystems in the selected area, including climate, soil characteristics, hydrological conditions, light intensity, etc. Plant genotype refers to the genetic composition of individual plants, specifically the entire genetic information carried by the plant, which determines the various traits of the plant, such as morphological characteristics, physiological functions, stress resistance and adaptability. In landscape planting planning, plant genotype is an important basis for selecting and configuring plant species, because it directly affects the growth performance and ecological adaptability of plants under specific environmental conditions.

[0025] This step uses a genetic algorithm to simulate the differences in the responses of different plant genotypes under specific environmental conditions based on the above-mentioned comprehensive terrain environment database. For example, during the simulation, the differences in the requirements of different plants for light intensity, water availability, and soil nutrients were taken into account, and a plant ecological adaptability prediction model was generated. Based on the model, the adaptability score of each plant in different areas was obtained, and the results of the intelligent assessment of ecological adaptability were generated. The results show that some drought-tolerant plants are more suitable for arid areas in the park, while moisture-loving plants should be planted preferentially near wetlands.

[0026] Step 103: Based on the ecological adaptability intelligent evaluation result, a three-dimensional virtual ecosystem model is constructed using a generative adversarial network in deep learning to simulate the natural growth process of multiple plants in a selected area and the interaction between plants, and to generate an optimal planting combination and layout scheme to be optimized. The optimal planting combination and layout scheme to be optimized is optimized by combining a user interactive function and a collaborative filtering algorithm to obtain a first target planting combination and layout scheme; In this step, the selected area refers to the specific geographical scope or plot determined after preliminary investigation and evaluation in the landscape planting planning project. The area has clear boundaries and contains specific ecological conditions, terrain features and biodiversity conditions. User interactive functions allow users to adjust the planting plan through the interface, such as changing the plant species, quantity and location. Collaborative filtering algorithms recommend the most appropriate planting combination and layout plan based on user preferences and historical choices.

[0027] This step uses the generative adversarial network in deep learning to build a three-dimensional virtual ecosystem model to simulate the natural growth process of various plants in the park and their interactions. Based on the results of the intelligent evaluation of ecological adaptability, a preliminary optimal planting combination and layout plan is generated. For example, the three-dimensional virtual ecosystem model shows the growth changes of different plants in the four seasons and the symbiotic relationship between them. These plans are further optimized by combining user interactive functions and collaborative filtering algorithms. Users can adjust the position and type of plants through the interface, and the system will provide real-time feedback on the adjusted effects, and finally obtain the first target planting combination and layout plan, such as planting ornamental flowers at the entrance of the park and arranging shade trees around the leisure area.

[0028] Step 104: using a style transfer algorithm and an emotion-aware interactive design method, the aesthetic elements in the artwork and the user preference feedback are integrated with the first target planting combination and layout scheme to obtain a final target planting combination and layout scheme; In order to make the design more aesthetic and personalized, the style transfer algorithm and emotion-aware interactive design method are used to incorporate the aesthetic elements of the artwork and the user's preference feedback into the first target planting combination and layout plan. For example, users can choose their favorite art style, such as impressionism or modern minimalist style, and the system will automatically adjust the color, shape and arrangement of the plants to match the selected art style. At the same time, through the emotion-aware interactive design method, the system will also adjust the plan according to the user's immediate feedback to ensure that the final target planting combination and layout plan is both scientific and reasonable, beautiful and practical.

[0029] Step 105: Based on the key monitoring points and indicators determined in the final target planting combination and layout plan, monitor the ecological environment of the planted area to obtain existing planting ecological data, and perform landscape garden planting planning management based on the final target planting combination and layout plan and the existing planting ecological data; In this step, key monitoring points and indicators refer to predetermined monitoring locations and evaluation criteria used to regularly check the ecological and environmental conditions of planted areas.

[0030] Based on the key monitoring points and indicators determined in the final target planting combination and layout plan, the ecological environment of the planted areas is monitored in real time through multiple monitoring stations, soil moisture sensors, weather stations, cameras and other equipment in the park. For example, soil moisture sensors can timely understand the moisture conditions near the plant roots to prevent over-irrigation or drought; weather stations record data such as temperature and precipitation to help assess the impact of climate change on plant growth. Based on these existing planting ecological data, planting planning and management are continuously optimized to ensure long-term ecological benefits and sustainable development.

[0031] The embodiment of the present invention ensures the scientificity and rationality of planting planning through a comprehensive data collection method, reduces decision-making errors caused by insufficient data, and improves the success rate of the project; improves the rationality and ecological benefits of plant configuration, ensures that the selected plants can grow healthily in the selected area, and reduces the subsequent maintenance costs; through the three-dimensional virtual model and user interaction function, not only the aesthetics and functionality of the plan are improved, but also the user's sense of participation and satisfaction are enhanced, ensuring the personalization and practicality of the design plan; the style transfer algorithm and the emotion-aware interactive design method enhance the artistic value of the design plan, and fully consider the personalized needs of the user, making the final plan more humane and creative; through real-time monitoring and optimization, the present invention can timely adjust and optimize the planting plan, ensure long-term ecological benefits and sustainable development, and at the same time improve management and maintenance efficiency.

[0032] After achieving accurate ecological adaptability assessment, in order to further optimize the planting plan of landscape gardening, the present invention provides a specific embodiment, step 103, based on the ecological adaptability intelligent assessment result, using the generative adversarial network in deep learning to construct a three-dimensional virtual ecosystem model to simulate the natural growth process of multiple plants in the selected area and the interaction between plants, generate the best planting combination and layout scheme to be optimized, combine the user interactive function and the collaborative filtering algorithm, optimize the best planting combination and layout scheme to be optimized, and obtain the first target planting combination and layout scheme, which specifically includes the following steps: Step 301: Based on the ecological adaptability intelligent assessment result, basic ecological and environmental parameters and dynamic environmental variables are obtained, and various parameters of the simulation engine of the virtual ecosystem are adjusted in combination with a multi-objective optimization algorithm to obtain a preliminary parameter configuration, and the preliminary parameter configuration is adjusted using Bayesian optimization technology to generate an optimal parameter configuration; In this step, basic ecological and environmental parameters include static environmental conditions such as soil type, light intensity, temperature, and humidity. Dynamic environmental variables include factors that change over time, such as seasonal changes, emergencies (such as floods and droughts). The various parameters of the simulation engine refer to the key settings for simulating the operation of the virtual ecosystem, such as growth rate, water absorption rate, etc.

[0033] For example, in a landscape project in a city park, based on the results of the intelligent assessment of ecological adaptability, the basic ecological and environmental parameters of the area (such as soil type is loam, average light time is 6 hours / day, and average annual temperature is 15°C), as well as dynamic environmental variables (such as changes in the four seasons of spring, summer, autumn and winter) were obtained. Combined with the multi-objective optimization algorithm, the various parameters of the virtual ecosystem simulation engine were adjusted. For example, the growth rate and water absorption rate of different plants were adjusted according to the evaluation results, and the preliminary parameter configuration was obtained. Then, these preliminary parameters were fine-tuned using Bayesian optimization technology, and finally the optimal parameter configuration was generated to ensure that the simulation results are closer to the actual situation.

[0034] Step 302: Based on the optimal parameter configuration, a conditional generative adversarial network is used to construct a target virtual ecosystem model, and a self-attention mechanism is introduced during the construction process to improve the conditional generative adversarial network architecture to optimize the construction process; In this step, the target virtual ecosystem model is constructed using a conditional generative adversarial network based on the above optimal parameter configuration. In order to further optimize the construction process, a self-attention mechanism is introduced into the conditional generative adversarial network architecture. For example, during the construction process, the self-attention mechanism helps the model better understand the interactions between different plants, such as how certain plants affect the humidity and light conditions of the surrounding environment. This makes the generated virtual ecosystem model more realistic and can accurately reflect the natural growth process and interactions of multiple plants in the selected area.

[0035] Step 303: Based on the target virtual ecosystem model, the natural growth process of multiple plants in the selected area and the interaction between the plants are simulated to obtain a target simulation result. Based on the target simulation result, a reinforcement learning algorithm is used to quantitatively evaluate the effects of different plant combinations to search for the best planting combination. This step simulates the natural growth process of various plants in the park and their interactions based on the target virtual ecosystem model. For example, the model shows the growth changes of different plants in the four seasons and the symbiotic relationship between them. Based on these target simulation results, the reinforcement learning algorithm is used to quantitatively evaluate the effects of different plant combinations. After multiple iterations, the best planting combination was finally searched out, such as planting moisture-loving plants near wetlands and selecting drought-tolerant plants in dry areas to ensure that each plant can grow in its most suitable environment.

[0036] Step 304: Analyze the spatial correlation between different plants in combination with the graph neural network, predict the growth trend of different plants and the impact of different plant growth on the surrounding environment based on the spatial correlation, obtain plant growth prediction results, and generate the optimal planting combination and layout plan to be optimized based on the optimal planting combination and the plant growth prediction results; In this step, spatial association refers to the spatial distribution of different plants and their mutual influence.

[0037] This step combines graph neural networks to analyze the spatial correlation between different plants and predict the growth trends of different plants and the impact of their growth on the surrounding environment. For example, graph neural network analysis shows that some tall trees will block sunlight and affect the photosynthesis of surrounding low plants; while plants with well-developed root systems may change the soil structure and increase water penetration. Based on these prediction results, the best planting combination is adjusted, and the best planting combination and layout plan to be optimized is generated to ensure that each plant can grow under the best conditions while reducing the negative impact on other plants.

[0038] Step 305: Introducing a user interactive function to preliminarily adjust key parameters of the target virtual ecosystem model according to specific design requirements, obtain the best planting combination and layout plan of intermediate optimization, apply a collaborative filtering algorithm to obtain successful examples of landscape planting planning, optimize the best planting combination and layout plan of intermediate optimization based on the successful examples of landscape planting planning, and obtain a first target planting combination and layout plan; In this step, key parameters refer to plant species and distribution, conditions, climate and seasonal characteristics, plant growth parameters, interaction parameters, spatial layout parameters, and aesthetic parameters. Successful examples of landscape planting planning refer to past successful landscape design cases, which serve as references to optimize the current plan.

[0039] By introducing user interactive functions, users can make preliminary adjustments to the key parameters of the target virtual ecosystem model according to specific design requirements to obtain the best planting combination and layout plan for intermediate optimization. For example, users can choose their favorite art style, and the system will automatically adjust the color, shape and arrangement of the plants to match the selected art style. Applying collaborative filtering algorithms, the system will also obtain successful examples of landscape planting planning from the database, further optimize the intermediate plan based on these examples, and finally obtain the first target planting combination and layout plan. For example, the system recommends a park-like design that contains a rich variety of local plant species and a reasonable spatial layout. Users can refer to these examples for adjustments to ensure that the design plan is both scientific and reasonable and beautiful and practical.

[0040] The embodiments of the present invention use methods such as simulation optimization by combining basic ecological and environmental parameters, dynamic variables with multi-objective optimization algorithms, etc., which not only improves the accuracy of virtual ecosystem simulation, but also enhances its adaptability to complex environmental changes, ensuring the scientificity and reliability of subsequent planning; by introducing the self-attention mechanism, the accuracy and stability of the virtual ecosystem model are significantly improved, making it closer to the actual situation, providing a reliable basis for subsequent analysis; the target virtual ecosystem model improves the rationality and ecological benefits of plant configuration, reduces the subsequent maintenance costs, and ensures the long-term stability and aesthetics of the design scheme; through the spatial correlation analysis of the graph neural network, the rationality of the plant layout is significantly improved, the unhealthy competition between plants is reduced, and the harmonious development of the ecosystem is promoted; through the application of user interactive functions and collaborative filtering algorithms, not only the user's sense of participation and satisfaction are enhanced, but also the experience of successful examples is fully utilized to ensure the personalization and practicality of the design scheme.

[0041] In order to meet the requirements of scientificity and ecological adaptability in landscape planting planning, the present invention provides a specific embodiment, based on which, step 303 simulates the natural growth process of multiple plants in a selected area and the interaction between plants based on the target virtual ecosystem model to obtain a target simulation result, and based on the target simulation result, uses a reinforcement learning algorithm to quantitatively evaluate the effects of different plant combinations to search for the best planting combination, specifically including the following steps: Step 311: Based on the optimal parameter configuration set in the target virtual ecosystem model, initial conditions and boundary conditions are defined, and plant individuals are initialized to simulate the natural growth process of multiple plants in the selected area and the interaction between plants, and obtain preliminary simulation results; In this step, initial conditions refer to the set values ​​at the beginning of the simulation, including soil moisture, temperature, light intensity, etc. Boundary conditions include long-term influencing factors such as historical meteorological data and biodiversity information. Plant individuals refer to the specific instances representing each plant in the simulation, including their location, size, health status, and other attributes.

[0042] For example, in a landscape project of a city park, initial conditions (such as soil moisture of 30%, average temperature of 15°C, and light duration of 6 hours / day) and boundary conditions (such as historical meteorological data of the past decade and biodiversity information in the region) were defined based on the optimal parameter configuration set in the target virtual ecosystem model. Then, a variety of plant individuals were initialized, including drought-tolerant herbs, moisture-loving trees, and local flowers. Through these settings, the natural growth process of these plants in the selected area and their interactions were simulated, and preliminary simulation results were obtained. For example, preliminary results show that some plants grow rapidly in spring, while their growth slows down in summer due to high temperatures.

[0043] Step 312: Introducing dynamic environmental variables and real-time feedback mechanisms into the simulation process to adjust the optimal parameter configuration according to the growth conditions of the individual plants and changes in the growth environment to optimize the simulation process, wherein the dynamic environmental variables include seasonal climate fluctuations and the impact of emergencies; In this step, dynamic environmental variables refer to factors that change over time, such as seasonal climate fluctuations and the impact of emergencies. The real-time feedback mechanism refers to real-time adjustment of simulation parameters according to the growth status of individual plants and changes in the growth environment to optimize the simulation process.

[0044] This step introduces dynamic environmental variables (such as temperature changes in spring, summer, autumn and winter, sudden drought events) and real-time feedback mechanisms during the simulation process. For example, when the simulation shows a decrease in precipitation over a period of time, the system automatically adjusts parameters such as water absorption rate and evaporation rate to adapt to the drought environment. In addition, according to the growth status of individual plants (such as leaf color changes and root development), the system updates the light intensity and temperature settings in real time to further optimize the simulation process. This dynamic adjustment makes the simulation results more in line with the actual situation and improves the accuracy of the prediction.

[0045] Step 313: Introduce multi-physics field coupling simulation technology to simulate the effects of multiple physical phenomena on plant growth at the same time, obtain physical simulation results, and combine the preliminary simulation results with the physical simulation results to determine target simulation results, wherein the target simulation results include key indicators and performance of interactions between plants, wherein the key indicators include plant growth rate, plant health index, and reproductive success rate, and the physical phenomena include hydrological cycle, heat conduction, and photosynthesis; In this step, key indicators refer to important parameters used to evaluate plant growth, such as growth rate, health index, and reproductive success rate. Physical phenomena refer to various physical processes that affect plant growth, such as hydrological cycle, heat conduction, and photosynthesis. Manifestations of plant interactions include symbiotic relationships, competitive relationships, etc.

[0046] In order to more comprehensively evaluate the growth of plants, multi-physics coupling simulation technology was introduced in the simulation process to simultaneously simulate the effects of multiple physical phenomena on plant growth and obtain physical simulation results. For example, by simulating the hydrological cycle, the impact of groundwater level changes on plant roots was analyzed; by simulating heat conduction, the impact of temperature changes in different seasons on plant metabolism was evaluated; by simulating photosynthesis, the impact of light intensity on plant photosynthetic efficiency was calculated. Combining the physical simulation results with the above preliminary simulation results, the target simulation results were determined, including key indicators (such as a plant growth rate of 10 cm per month, a health index of 90%, and a reproductive success rate of 85%) and the performance of interactions between plants (such as some plants blocking sunlight and affecting the photosynthesis of surrounding plants). These results provide a scientific basis for subsequent planting planning.

[0047] More specifically, the present invention provides a calculation formula for a target simulation result to meet the needs of multi-factor coupling in the plant growth process. The formula integrates preliminary simulation results, the influence of physical phenomena, interactions between plants, and dynamic optimization and real-time feedback mechanisms. In addition, considering that plant growth involves knowledge from multiple disciplines such as biology, ecology, and physics, a multi-physics field coupling function is introduced to ensure the scientificity and reliability of the formula. At the same time, in order to meet the personalized needs of different landscape projects, the formula also incorporates user interactive functions and collaborative filtering algorithms, so that the final optimal planting combination and layout plan can better reflect user preferences and specific needs. The specific calculation formula is as follows: ; in, Represents the target simulation result, taking into account the preliminary simulation results , Physical simulation results , plant-plant interaction model , adaptive adjustment algorithm And multiphysics coupling functions The impact of It represents the time step, which indicates the time point or time period of the simulation; Represents a multi-physics field coupling simulation function, which is used to generate the final target simulation results; Among them, the specific expressions of each parameter involved in the formula are as follows: ; ; ; ; ; represents preliminary simulation results, which represent the results of a series of simulation runs conducted under initial and boundary conditions; It represents the time step, which indicates the time point or time period of the simulation; Indicates the spatial position, indicating the specific position coordinates within the simulation area; Represents the initialized plant individual status, including the location, size, health status and other attributes of each plant individual; represents the preliminary simulation function, which is used to calculate the preliminary simulation results based on the initial conditions; It represents the results of physical simulation, taking into account the effects of physical phenomena such as hydrological cycle, heat conduction, photosynthesis, etc. on plant growth; Parameter configurations that represent physical phenomena, such as hydrological cycle rate, thermal conductivity, photosynthesis efficiency, etc.; Represents the initial conditions of physical phenomena, such as soil moisture, air temperature, light intensity, etc.; Represents a physical simulation function, which is used to calculate simulation results based on physical phenomena; Represents the plant interaction model, which is used to evaluate the symbiotic relationship, competitive relationship, etc. between different plants; Represents the state set of all plants, including their location, size, health status, etc.; Indicates environmental conditions such as soil nutrients, water availability, etc.; represents the interaction function, which is used to evaluate the mutual influence between plants; It represents the adaptive adjustment algorithm, which dynamically optimizes the parameter configuration during the simulation process according to the real-time feedback mechanism; It represents the optimal parameter configuration, the best ecological and environmental parameters obtained through preliminary analysis and optimization; Represents dynamic environmental variables, such as seasonal climate fluctuations, impacts of emergencies, etc.; Indicates the growth status of individual plants, such as height, leaf area, root depth, etc.; Represents a user interactive feedback model that collects user preferences and suggestions to optimize simulation results; Represents an adaptive adjustment function, which is used to dynamically optimize simulation parameters; Represents the multi-physics coupling function, which is used to integrate the simulation results of multiple physical phenomena and consider their mutual influence; represents the coupling function used to integrate the effects of physical phenomena and interactions between plants.

[0048] This formula significantly improves the accuracy of predictions by integrating multiple influencing factors, making it applicable to different types of ecosystems and environmental conditions. By quantitatively evaluating the effects of different plant combinations and optimizing planting plans in combination with user interactive functions, it not only helps to rationally plan plant species and quantities and maximize the use of land resources, but also provides a scientific basis for landscape designers and managers to support them in making more reasonable planting plans and management decisions. In addition, detailed target simulation results and key indicators provide strong support for scientific decision-making, while user interactive functions enhance user experience, ensuring that the final plan meets both aesthetic needs and functionality, thereby maximizing ecological and economic benefits.

[0049] Step 314: Based on the target simulation result, a reinforcement learning algorithm is applied to quantitatively evaluate the effects of different plant combinations to generate an optimal planting combination suitable for the selected area; Based on the above target simulation results, this step uses reinforcement learning algorithms to quantitatively evaluate the effects of different plant combinations. For example, the system evaluates the performance of different plant combinations in the selected area based on key indicators such as plant growth rate, health index, and reproductive success rate. Through multiple iterations and optimizations, the system finally searches for the best planting combination. For example, moisture-loving plants are selected near wetlands, and drought-tolerant plants are selected in dry areas to ensure that each plant can grow in its most suitable environment, while reducing unhealthy competition among plants and promoting the harmonious development of the ecosystem.

[0050] The embodiment of the present invention provides a solid foundation for subsequent simulations by defining the conditions required for simulation, ensuring the accuracy and reliability of simulation results, and reflecting the growth characteristics of different plants in specific environments; by introducing dynamic environmental variables and real-time feedback mechanisms, the flexibility and adaptability of simulations are significantly enhanced, ensuring that simulation results can truly reflect the impact of environmental changes on plant growth; the application of multi-physics field coupling simulation technology significantly improves the comprehensiveness and accuracy of simulations, ensuring a comprehensive assessment of plant growth conditions, and providing strong support for optimizing planting plans; through the quantitative evaluation of reinforcement learning algorithms, the rationality and ecological benefits of plant configurations are significantly improved, ensuring the scientificity and sustainability of the design plan, and reducing subsequent maintenance costs.

[0051] In order to build a scientific and comprehensive foundation for landscape planting planning, the present invention provides a specific embodiment, based on which, step 101, collecting comprehensive environment and biodiversity data to generate a comprehensive terrain environment database, the comprehensive environment and biodiversity data including surface images, meteorological historical data, soil type distribution maps and biodiversity census information, specifically including the following steps: Step 111: using multi-source heterogeneous data fusion technology to collect comprehensive environment and biodiversity data, pre-processing the comprehensive environment and biodiversity data, and generating a multi-source data set; For example, in a landscape project in a city park, multi-source heterogeneous data fusion technology was used to collect comprehensive environmental and biodiversity data from multiple sources, including satellite remote sensing, drone aerial photography, ground photography, meteorological station records, soil sampling reports, and biodiversity surveys. These data include surface images, historical meteorological data for the past decade, soil type distribution maps, and detailed biodiversity census information. Through preprocessing steps such as data cleaning, format conversion, and missing value filling, a multi-source dataset containing all relevant information was generated. For example, surface images of different resolutions were unified into the same spatial reference system, and missing values ​​in some meteorological data were filled to ensure data consistency and integrity.

[0052] Step 112: applying a generative adversarial network and a convolutional neural network in deep learning to perform intelligent enhancement processing on the surface images and meteorological data in the multi-source dataset, by generating images of missing areas of the multi-source dataset, and simultaneously identifying and annotating key features in the multi-source dataset to generate an enhanced dataset, wherein the key features include vegetation coverage and land use type; This step applies the generative adversarial network and convolutional neural network in deep learning to intelligently enhance the surface images and meteorological data in the multi-source dataset. For example, the generative adversarial network is used to generate high-resolution surface images of the missing areas in the multi-source dataset, and the convolutional neural network is used to identify and annotate key features in the image, such as vegetation coverage and land use type. By enhancing the meteorological data, some missing historical meteorological records are supplemented, further improving the dataset. Finally, an enhanced dataset containing rich information is generated to ensure the integrity and accuracy of the data.

[0053] Step 113: combining the time dimension and the space dimension in the enhanced data set using a space-time cube model to generate a space-time evolution diagram to reflect the environmental dynamics in the selected area; In this step, the spatiotemporal evolution diagram refers to a diagram generated based on the spatiotemporal cube model, which reflects the trend and pattern of environmental changes in the selected area.

[0054] In order to comprehensively capture and analyze the environmental dynamics in the selected area, we used the space-time cube model to combine the time dimension and space dimension in the enhanced dataset to generate a space-time evolution map. For example, in a certain urban park project, the space-time evolution map shows the changes in surface cover, temperature fluctuations, and precipitation changes in different seasons over the past decade. In this way, it can not only intuitively reflect the changing trends and patterns of the environment in the region, but also provide strong data support for subsequent ecological adaptability assessments and planting plans.

[0055] Step 114: applying a graph neural network to analyze the correlation between different locations in the spatiotemporal evolution graph to identify target locations that have mutual influence within a specific time period, and predicting environmental evolution based on the target locations; In this step, the target sites are those where there are mutual influences within a specific time period, such as the relationship between wetlands and surrounding grasslands.

[0056] In this step, graph neural networks are used to analyze the correlation between different locations in the spatiotemporal evolution diagram, and target locations that have mutual influence within a specific time period are identified. For example, through graph neural network analysis, it is found that there is a significant water exchange and plant symbiosis between wetlands and surrounding grasslands. Based on these target locations, the evolution of the future environment is predicted, such as the possibility of wetland expansion and its impact on the surrounding ecosystem. This prediction helps to take into account potential ecological changes in the planning stage to optimize planting plans.

[0057] Step 115: constructing a comprehensive terrain environment database based on the enhanced data set, the spatiotemporal evolution graph, and the environmental evolution situation; This step builds a comprehensive terrain environment database based on the above enhanced datasets, spatiotemporal evolution maps, and environmental evolution. The database not only contains rich multi-source heterogeneous data, but also includes detailed spatiotemporal evolution maps and predictions of future environmental changes. For example, the database records historical data on land cover changes, temperature, and precipitation in different regions, as well as possible wetland expansion and plant migration in the future. This comprehensive database provides comprehensive data support for landscape planting planning, ensuring the scientific and forward-looking nature of the planning.

[0058] The embodiments of the present invention can achieve the following beneficial effects through the above steps: the enhanced data set significantly improves the quality and richness of the data set, making subsequent analysis and prediction more accurate and reliable, and enhancing the generalization ability of the space-time cube model; the space-time cube model is used for prediction to achieve accurate monitoring and prediction of environmental changes, ensure the scientific nature and foresight of landscape design, and improve the long-term stability and sustainability of the planning; through the application of graph neural networks, the understanding of the correlation between different locations is significantly improved, the ecological friendliness and long-term stability of the design scheme are ensured, and the harmonious development of the ecosystem is promoted; by constructing a comprehensive terrain environment database, the efficiency of data management and utilization is significantly improved, the scientific nature and long-term stability of the planning are ensured, and strong support is provided for landscape design.

[0059] In order to comprehensively capture and analyze the environmental dynamics in the selected area, based on this, the present invention provides a specific embodiment, step 113, using the space-time cube model to combine the time dimension and the space dimension in the enhanced data set to generate a space-time evolution diagram to reflect the environmental dynamics in the selected area, specifically including the following steps: Step 121: Based on the enhanced data set, combined with planning management objectives and data characteristics, determine the time granularity and spatial resolution of the space-time cube model; In this step, planning and management objectives refer to the specific objectives of landscape planting planning, such as ecological protection, aesthetic design, or functional optimization. Data characteristics refer to the specific attributes and characteristics of the comprehensive environment and biodiversity data in the enhanced dataset, including data type, data frequency, and data integrity. Time granularity refers to the degree of fineness of division in the time dimension, such as by hour, day, month, etc. Spatial resolution refers to the degree of fineness of division in the spatial dimension, such as per meter, per hundred meters, etc.

[0060] For example, in a landscape project in an urban park, based on the enhanced dataset, combined with planning and management goals (such as long-term ecological monitoring) and data characteristics (such as high-frequency recording of meteorological data), the time granularity of the space-time cube model is determined to be daily and the spatial resolution is 10 meters. This setting ensures accurate capture and analysis of environmental changes, such as being able to carefully reflect daily temperature changes and vegetation coverage of different plots, meeting the needs of long-term ecological monitoring in the park.

[0061] Step 122: Based on the temporal granularity and spatial resolution, applying spatial indexing technology, indexing the enhanced comprehensive environment and biodiversity data in the enhanced data set to generate an optimized index structure; Based on the time granularity and spatial resolution determined above, this step uses spatial indexing technology to index the comprehensive environment and biodiversity data in the enhanced dataset. For example, the R-tree indexing method is used to spatially index surface images and meteorological data, generating an optimized index structure. This enables the system to quickly locate and extract the required information when querying data at a specific time and location, significantly improving data access efficiency. For example, users can quickly obtain soil moisture and plant species distribution of a plot of land within a certain period of time.

[0062] Step 123: Based on the optimized index structure, the enhanced integrated environment and biodiversity data are mapped to corresponding spatiotemporal positions to generate a spatiotemporal cube model. In the process of generating the spatiotemporal cube model, a spatiotemporal interpolation algorithm is used to add missing data points to optimize the spatiotemporal cube model. This step maps the enhanced integrated environment and biodiversity data to the corresponding spatiotemporal locations based on the optimized index structure to generate a space-time cube model. During the generation process, the space-time interpolation algorithm was used to add missing data points and optimize the space-time cube model. For example, when data from some weather stations were missing, the precipitation in that time period was estimated through the interpolation algorithm to ensure the integrity and continuity of the data. The final space-time cube model not only covers all known data points, but also fills in the missing parts, providing a comprehensive space-time perspective.

[0063] Step 124: Combining the space-time cube model and the three-dimensional visualization engine, visualizing the environmental changes in the selected area, and generating a space-time evolution diagram to reflect the environmental dynamics in the selected area; This step combines the generated space-time cube model and the 3D visualization engine to visualize the environmental changes in the selected area and generate a space-time evolution map. For example, in a city park project, the space-time evolution map shows the changes in surface cover, temperature fluctuations, and precipitation changes in different seasons over the past decade. Through the 3D visualization engine, users can intuitively see the process of wetland expansion, tree growth, and grassland changes, and clearly understand the dynamic evolution of the environment in the park. This visualization tool not only helps planners better understand environmental changes, but also shows the ecological benefits of the project to the public.

[0064] The embodiment of the present invention ensures that the space-time cube model can capture short-term dynamic changes and conduct long-term trend analysis through the time granularity and spatial resolution of the space-time cube model, thereby improving the practicality and accuracy of the model; by applying spatial indexing technology, the data retrieval speed and efficiency are significantly improved, ensuring the real-time and accuracy of subsequent analysis and visualization; by applying the space-time interpolation algorithm, the integrity and continuity of the space-time cube model are significantly improved, ensuring the comprehensive capture and analysis of environmental changes, and enhancing the reliability and practicality of the model; by combining the space-time cube model and the three-dimensional visualization engine, the intuitive understanding and display effect of environmental changes are significantly improved, the scientific nature and transparency of planning decisions are enhanced, and public participation and recognition are promoted.

[0065] In order to meet the demand for accurate assessment of plant ecological adaptability in landscape planting planning, based on this, the present invention provides a specific embodiment, step 102, based on the comprehensive terrain environment database, using a genetic algorithm to simulate the response differences of different plant genotypes under specific environmental conditions to generate a plant ecological adaptability prediction model, based on the plant ecological adaptability prediction model, generating an ecological adaptability intelligent assessment result, specifically comprising the following steps: Step 201: Select target environmental variables and plant genotypes based on the comprehensive terrain environment database; In this step, the comprehensive terrain environment database refers to a comprehensive database containing surface images, meteorological historical data, soil type distribution maps, and biodiversity census information to support landscape planting planning. The target environmental variables refer to key environmental factors selected from the comprehensive terrain environment database according to the specific conditions of the selected area, such as temperature, precipitation, light intensity, etc.

[0066] For example, in a landscape project for an urban park, target environmental variables (such as an average annual temperature of 15°C, precipitation of 800 mm, and soil pH of 6.5) and specific plant genotypes (such as drought-tolerant herbs and moisture-loving trees) were selected based on a comprehensive terrain environment database. These selections were based on the needs of different ecological zones within the park, such as wetlands requiring moisture-loving plants, while dry areas were suitable for drought-tolerant plants. In this way, it was ensured that the selected plants could grow healthily in a specific environment and coexist harmoniously with the surrounding ecosystem.

[0067] Step 202: Based on the target environmental variables and plant genotypes, using a genetic algorithm to simulate the response differences of different plant genotypes under specific environmental conditions to generate a plant ecological adaptability prediction model to be optimized; This step uses genetic algorithms to simulate the differences in the responses of different plant genotypes under specific environmental conditions based on the target environmental variables and plant genotypes selected above. For example, during the simulation, the different requirements of drought-tolerant herbaceous plants and moisture-loving trees for water, light, and temperature were taken into account, and a prediction model for the ecological adaptability of plants to be optimized was generated. This model preliminarily predicts the growth rate and health status of each plant under different environmental conditions, providing a basis for subsequent optimization.

[0068] Step 203: applying a reinforcement learning algorithm, defining a reward function by combining multiple evaluation indicators, evaluating the adaptability scores of different plant combinations based on the reward function, optimizing the plant ecological adaptability prediction model to be optimized based on the adaptability scores, and obtaining a plant ecological adaptability prediction model, wherein the evaluation indicators include plant growth rate, stress resistance, and aesthetic value; In this step, the evaluation index refers to the key parameters used to evaluate the adaptability of plant combinations, including plant growth rate, stress resistance, and aesthetic value. The reward function defines how to calculate the adaptability score of each plant combination based on the evaluation index to guide model optimization. The adaptability score refers to the result calculated based on the reward function, which reflects the overall adaptability of the plant combination under specific environmental conditions.

[0069] This step applies a reinforcement learning algorithm and combines multiple evaluation indicators (such as plant growth rate, stress resistance, and aesthetic value) to define a reward function to evaluate the adaptability scores of different plant combinations. For example, the system calculates the growth rate, stress resistance, and aesthetic value of each plant combination based on the simulation results and assigns corresponding reward scores. Based on these adaptability scores, the system continuously adjusts and optimizes the plant ecological adaptability prediction model, and finally obtains a more accurate and reliable plant ecological adaptability prediction model. For example, some plant combinations show higher growth rates and aesthetic values ​​in humid environments, and therefore obtain higher adaptability scores.

[0070] Step 204: Based on the plant ecological adaptability prediction model, predict and analyze the interactions between different plants and the impacts of different plants on the ecosystem to generate an ecological adaptability intelligent assessment result; In this step, interactions refer to symbiotic relationships, competitive relationships, etc. between different plants. Ecosystem impacts refer to the effects of plant growth on ecosystem elements such as soil, water quality, and air quality.

[0071] This step is based on the plant ecological adaptability prediction model, which predicts and analyzes the interactions between different plants and their impacts on the ecosystem, and generates ecological adaptability intelligent assessment results. For example, the plant ecological adaptability prediction model shows that some tall trees will block sunlight and affect the photosynthesis of surrounding low plants; while plants with well-developed root systems may change soil structure and increase water infiltration. In addition, the impact of plant growth on soil fertility, water quality and air quality is also predicted. Based on these predictive analyses, ecological adaptability intelligent assessment results are generated to ensure that each plant can grow in its most suitable environment while reducing negative impacts on other plants and ecosystems.

[0072] The embodiment of the present invention ensures the adaptability and ecological benefits of the selected plants in the selected area through the above steps, and improves the scientificity and rationality of the planting plan. Through the simulation of the genetic algorithm, the accuracy and reliability of the model are significantly improved, which can more realistically reflect the growth performance of plants in a specific environment, and provide a solid foundation for subsequent optimization; through the application of the reinforcement learning algorithm, the accuracy and reliability of the plant ecological adaptability prediction model are significantly improved, ensuring the optimal adaptability of the selected plant combination under specific environmental conditions, and improving the scientificity and practicality of the planting plan; through detailed predictive analysis, the understanding of plant interactions and ecosystem impacts is significantly improved, ensuring the ecological friendliness and long-term stability of the planting plan, and promoting the harmonious development of the ecosystem.

[0073] In order to achieve a perfect combination of aesthetics and functionality in landscape planting planning, based on this, the present invention provides a specific embodiment, step 104, using a style transfer algorithm and an emotion perception interactive design method, integrating the aesthetic elements in the artwork and the user preference feedback with the first target planting combination and layout scheme, and obtaining the final target planting combination and layout scheme, specifically comprising the following steps: Step 401: extracting aesthetic elements from artworks using a style transfer algorithm in deep learning, where the aesthetic elements include color palettes, texture features, and spatial layout patterns; In this step, aesthetic elements include color palette, texture characteristics, and spatial layout patterns, which together determine the visual beauty and artistic style of the landscape.

[0074] For example, in a landscape project for a city park, the style transfer algorithm in deep learning was used to extract aesthetic elements from a series of famous works of art (such as Van Gogh's "Starry Night"). For example, the unique color palette (such as the contrast between dark blue and yellow), texture features (such as swirling brushstrokes), and spatial layout patterns (such as the dynamic combination of sky and ground) were extracted from "Starry Night". In this way, the aesthetic elements of the artwork were incorporated into the design of the park, ensuring that the design plan was both scientific and artistic.

[0075] Step 402: Collect user preference feedback using an emotion-aware interaction design method to obtain user preferences and emotional response information to different landscape elements, wherein the emotion-aware interaction design method includes a questionnaire survey, a focus group discussion, and an eye tracking experiment; In this step, the eye tracking experiment refers to recording the user's eye movement path when observing the landscape design and analyzing their focus and areas of interest.

[0076] In order to better understand users' preferences and emotional responses, an emotion-aware interactive design method was adopted. Specifically, a questionnaire survey was issued to collect users' preferences for different plant species and landscape elements; focus group discussion information was released to collect users' needs and expectations for park functional areas; and an eye tracking experiment was conducted to record users' eye movement paths when observing preliminary design plans and analyze the design parts they were most interested in. For example, the questionnaire survey showed that most users liked natural-style landscapes, the focus group discussion revealed users' needs for leisure areas, and the eye tracking experiment showed that users paid special attention to the design of the entrance.

[0077] Step 403: constructing a cross-domain transfer learning model to integrate the aesthetic elements, the preference and emotional response information, and the first target planting combination and layout plan to obtain a final target planting combination and layout plan; In order to effectively integrate the above aesthetic elements, user preferences and emotional response information with the first target planting combination and layout plan, a cross-domain transfer learning model was constructed. The model combines the aesthetic elements in the artwork (such as color palette, texture features and spatial layout pattern) with the preference and emotional response information provided by the user, and further optimizes the initial planting combination and layout plan. For example, according to the user's preference for natural style, the model adjusts the color matching and spatial layout of the plants to make it more in line with the user's aesthetic needs; at the same time, combined with the results of the eye tracking experiment, the landscape design at the entrance is optimized to highlight the key areas. Finally, a final target planting combination and layout plan that is both scientific and reasonable, beautiful and practical is obtained.

[0078] The embodiment of the present invention not only improves the artistic value of the design scheme through the style transfer algorithm, but also makes the final scheme more creative and personalized, thereby enhancing the user's aesthetic experience; through the multi-dimensional emotion perception interaction design method, the user's preference and emotional response information are comprehensively collected to ensure that the design scheme is more in line with the user's actual needs and expectations, thereby improving user satisfaction; by constructing a cross-domain transfer learning model, the aesthetic elements, user preferences and emotional response information are successfully integrated into the planting plan, which significantly improves the personalization and practicality of the design scheme, thereby ensuring that the final scheme can both meet ecological requirements and provide a good user experience.

[0079] Figure 2 The present invention provides a structural schematic diagram of a landscape planting planning and management system based on terrain environment analysis, such as Figure 2 As shown, the system includes: A collection module 21 is used to collect comprehensive environment and biodiversity data to generate a comprehensive terrain environment database, wherein the comprehensive environment and biodiversity data includes surface images, meteorological historical data, soil type distribution maps, and biodiversity census information; A simulation module 22 is used to simulate the response differences of different plant genotypes under specific environmental conditions using a genetic algorithm based on the comprehensive terrain environment database to generate a plant ecological adaptability prediction model, and generate an ecological adaptability intelligent evaluation result based on the plant ecological adaptability prediction model; A generation module 23 is used to construct a three-dimensional virtual ecosystem model based on the ecological adaptability intelligent evaluation result by using a generative adversarial network in deep learning to simulate the natural growth process of multiple plants in a selected area and the interaction between plants, generate an optimal planting combination and layout scheme to be optimized, and optimize the optimal planting combination and layout scheme to be optimized by combining a user interactive function and a collaborative filtering algorithm to obtain a first target planting combination and layout scheme; An optimization module 24 is used to use a style transfer algorithm and an emotion perception interaction design method to integrate the aesthetic elements in the artwork and the user preference feedback with the first target planting combination and layout scheme to obtain a final target planting combination and layout scheme; Management module 25 is used to monitor the ecological environment of the planted area based on the key monitoring points and indicators determined in the final target planting combination and layout plan, obtain the existing planting ecological data, and perform landscape planting planning management based on the final target planting combination and layout plan and the existing planting ecological data.

[0080] Figure 2 The landscape gardening planting planning management system based on terrain environment analysis can be executed Figure 1The implementation principle and technical effect of the landscape planting planning management method based on terrain environment analysis described in the illustrated embodiment will not be described in detail. The specific manner in which each module and unit performs operations in the landscape planting planning management system based on terrain environment analysis in the above embodiment has been described in detail in the embodiment of the method, and will not be described in detail here.

[0081] In one possible design, Figure 2 A landscape planting planning and management system based on terrain environment analysis in the illustrated embodiment can be implemented as a computing device, such as Figure 3 As shown, the computing device may include a storage component 31 and a processing component 32; The storage component 31 stores one or more computer instructions, wherein the one or more computer instructions are called and executed by the processing component 32 .

[0082] The processing component 32 is used to: collect comprehensive environmental and biodiversity data to generate a comprehensive terrain environment database, wherein the comprehensive environmental and biodiversity data includes surface images, meteorological historical data, soil type distribution maps, and biodiversity census information; based on the comprehensive terrain environment database, use a genetic algorithm to simulate the response differences of different plant genotypes under specific environmental conditions to generate a plant ecological adaptability prediction model, and based on the plant ecological adaptability prediction model, generate an ecological adaptability intelligent evaluation result; based on the ecological adaptability intelligent evaluation result, use a generative adversarial network in deep learning to construct a three-dimensional virtual ecosystem model to simulate the natural growth process of multiple plants in a selected area and the interactions between plants. Interact with each other to generate the best planting combination and layout plan to be optimized, combine the user interactive function and the collaborative filtering algorithm to optimize the best planting combination and layout plan to be optimized, and obtain the first target planting combination and layout plan; adopt the style transfer algorithm and the emotion perception interactive design method to integrate the aesthetic elements in the artwork and the user preference feedback with the first target planting combination and layout plan to obtain the final target planting combination and layout plan; based on the key monitoring points and indicators determined in the final target planting combination and layout plan, monitor the ecological environment of the planted area to obtain the existing planting ecological data, and carry out landscape planting planning and management based on the final target planting combination and layout plan and the existing planting ecological data.

[0083] The processing component 32 may include one or more processors to execute computer instructions to complete all or part of the steps in the above method. Of course, the processing component may also be implemented by one or more application-specific integrated circuits (ASICs), digital signal processors (DSPs), digital signal processing devices (DSPDs), programmable logic devices (PLDs), field programmable gate arrays (FPGAs), controllers, microcontrollers, microprocessors or other electronic components to perform the above method.

[0084] The storage component 31 is configured to store various types of data to support operations at the terminal. The storage component can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic memory, flash memory, magnetic disk or optical disk.

[0085] Of course, the computing device may also include other components, such as input / output interfaces, display components, communication components, etc.

[0086] The input / output interface provides an interface between the processing component and the peripheral interface module, which may be an output device, an input device, etc.

[0087] The communication component is configured to facilitate, among other things, wired or wireless communications between the computing device and other devices.

[0088] Among them, the computing device can be a physical device or an elastic computing host provided by a cloud computing platform, etc. In this case, the computing device can refer to a cloud server, and the above-mentioned processing components, storage components, etc. can be basic server resources rented or purchased from the cloud computing platform.

[0089] The embodiment of the present invention further provides a computer storage medium storing a computer program, which can achieve the above-mentioned Figure 1 The illustrated embodiment is a landscape planting planning and management method based on terrain environment analysis.

[0090] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0091] The device embodiments described above are merely illustrative, wherein the units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they may be located in one place, or they may be distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the scheme of this embodiment. Ordinary technicians in this field can understand and implement it without paying creative labor.

[0092] Through the description of the above implementation methods, those skilled in the art can clearly understand that each implementation method can be implemented by means of software plus a necessary general hardware platform, and of course, can also be implemented by hardware. Based on this understanding, the above technical solution is essentially or the part that contributes to the prior art can be embodied in the form of a software product, and the computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, a disk, an optical disk, etc., including a number of instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods described in each embodiment or some parts of the embodiments.

[0093] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A landscape gardening planting planning and management method based on terrain environment analysis, characterized in that: include: Collecting comprehensive environmental and biodiversity data to generate a comprehensive terrain environmental database, the comprehensive environmental and biodiversity data including surface images, historical meteorological data, soil type distribution maps, and biodiversity census information; Based on the comprehensive terrain environment database, a genetic algorithm is used to simulate the response differences of different plant genotypes under specific environmental conditions to generate a plant ecological adaptability prediction model, and based on the plant ecological adaptability prediction model, an ecological adaptability intelligent evaluation result is generated; Based on the ecological adaptability intelligent assessment result, a three-dimensional virtual ecosystem model is constructed using a generative adversarial network in deep learning to simulate the natural growth process of multiple plants in a selected area and the interaction between plants, and to generate an optimal planting combination and layout scheme to be optimized. The optimal planting combination and layout scheme to be optimized is optimized by combining user interactive functions and collaborative filtering algorithms to obtain a first target planting combination and layout scheme; Using a style transfer algorithm and an emotion-aware interactive design method, the aesthetic elements in the artwork and user preference feedback are integrated with the first target planting combination and layout scheme to obtain the final target planting combination and layout scheme; Based on the key monitoring points and indicators determined in the final target planting combination and layout plan, the ecological environment of the planted area is monitored to obtain the existing planting ecological data, and landscape planting planning and management are carried out based on the final target planting combination and layout plan and the existing planting ecological data.

2. The method according to claim 1, characterized in that Based on the ecological adaptability intelligent assessment results, a three-dimensional virtual ecosystem model is constructed using a generative adversarial network in deep learning to simulate the natural growth process of multiple plants in a selected area and the interaction between plants, and to generate the best planting combination and layout scheme to be optimized. The best planting combination and layout scheme to be optimized are optimized by combining user interactive functions and collaborative filtering algorithms to obtain a first target planting combination and layout scheme, including: Based on the results of the intelligent assessment of ecological adaptability, basic ecological and environmental parameters and dynamic environmental variables are obtained, and the various parameters of the simulation engine of the virtual ecosystem are adjusted in combination with a multi-objective optimization algorithm to obtain a preliminary parameter configuration, and the preliminary parameter configuration is adjusted using Bayesian optimization technology to generate an optimal parameter configuration; Based on the optimal parameter configuration, a conditional generative adversarial network is used to construct a target virtual ecosystem model, and a self-attention mechanism is introduced during the construction process to improve the conditional generative adversarial network architecture to optimize the construction process; Based on the target virtual ecosystem model, the natural growth process of multiple plants in the selected area and the interaction between the plants are simulated to obtain a target simulation result. Based on the target simulation result, a reinforcement learning algorithm is used to quantitatively evaluate the effects of different plant combinations to search for the best planting combination. Analyze the spatial correlation between different plants in combination with graph neural network, predict the growth trend of different plants and the impact of different plant growth on the surrounding environment based on the spatial correlation, obtain plant growth prediction results, and generate the best planting combination and layout plan to be optimized based on the best planting combination and the plant growth prediction results; A user interactive function is introduced to make preliminary adjustments to the key parameters of the target virtual ecosystem model according to specific design requirements, so as to obtain the best planting combination and layout scheme of intermediate optimization, and a collaborative filtering algorithm is applied to obtain successful examples of landscape planting planning, so as to optimize the best planting combination and layout scheme of intermediate optimization based on the successful examples of landscape planting planning, and obtain the first target planting combination and layout scheme.

3. The method according to claim 2, characterized in that Based on the target virtual ecosystem model, the natural growth process of multiple plants in the selected area and the interaction between the plants are simulated to obtain the target simulation results. Based on the target simulation results, the reinforcement learning algorithm is used to quantitatively evaluate the effects of different plant combinations to search for the best planting combination, including: Based on the optimal parameter configuration set in the target virtual ecosystem model, the initial conditions and boundary conditions are defined, and plant individuals are initialized to simulate the natural growth process of multiple plants in the selected area and the interaction between plants, and obtain preliminary simulation results; Introducing dynamic environmental variables and real-time feedback mechanisms in the simulation process to adjust the optimal parameter configuration according to the growth conditions of the individual plants and changes in the growth environment to optimize the simulation process, wherein the dynamic environmental variables include seasonal climate fluctuations and the impact of emergencies; Introducing multi-physics field coupling simulation technology, simulating the effects of multiple physical phenomena on plant growth at the same time, obtaining physical simulation results, combining the preliminary simulation results with the physical simulation results, determining target simulation results, the target simulation results including key indicators and the performance of interactions between plants, the key indicators including plant growth rate, plant health index and reproductive success rate, and the physical phenomena including hydrological cycle, heat conduction and photosynthesis; Based on the target simulation results, a reinforcement learning algorithm is applied to quantitatively evaluate the effects of different plant combinations to generate an optimal planting combination suitable for the selected area.

4. The method according to claim 1, characterized in that: Collect comprehensive environmental and biodiversity data to generate a comprehensive terrain environmental database, including surface images, historical meteorological data, soil type distribution maps, and biodiversity census information, including: Using multi-source heterogeneous data fusion technology to collect comprehensive environment and biodiversity data, pre-process the comprehensive environment and biodiversity data, and generate a multi-source data set; Applying generative adversarial networks and convolutional neural networks in deep learning to intelligently enhance the surface images and meteorological data in the multi-source dataset, generating images of missing areas of the multi-source dataset, and identifying and annotating key features in the multi-source dataset to generate an enhanced dataset, wherein the key features include vegetation coverage and land use type; Combining the time dimension and the space dimension in the enhanced data set by using a space-time cube model to generate a space-time evolution map to reflect the environmental dynamics in the selected area; Applying a graph neural network to analyze the correlation between different locations in the spatiotemporal evolution graph to identify target locations that have mutual influence within a specific time period, and predicting environmental evolution based on the target locations; A comprehensive terrain environment database is constructed based on the enhanced data set, the spatiotemporal evolution diagram and the environmental evolution situation.

5. The method according to claim 4, characterized in that The space-time cube model is used to combine the time dimension and space dimension in the enhanced dataset to generate a space-time evolution map to reflect the environmental dynamics in the selected area, including: Based on the enhanced data set, combined with planning management objectives and data characteristics, determine the time granularity and spatial resolution of the space-time cube model; Based on the temporal granularity and spatial resolution, applying spatial indexing technology, indexing the enhanced comprehensive environment and biodiversity data in the enhanced data set to generate an optimized index structure; Based on the optimized index structure, the enhanced integrated environment and biodiversity data are mapped to corresponding spatiotemporal locations to generate a spatiotemporal cube model, and in the process of generating the spatiotemporal cube model, a spatiotemporal interpolation algorithm is used to add missing data points to optimize the spatiotemporal cube model; By combining the space-time cube model and the three-dimensional visualization engine, the environmental changes in the selected area are visualized to generate a space-time evolution diagram to reflect the environmental dynamics in the selected area.

6. The method according to claim 1, characterized in that Based on the comprehensive terrain environment database, a genetic algorithm is used to simulate the response differences of different plant genotypes under specific environmental conditions to generate a plant ecological adaptability prediction model. Based on the plant ecological adaptability prediction model, an ecological adaptability intelligent evaluation result is generated, including: selecting target environmental variables and plant genotypes based on the comprehensive terrain environmental database; Based on the target environmental variables and plant genotypes, using a genetic algorithm to simulate the response differences of different plant genotypes under specific environmental conditions to generate a plant ecological adaptability prediction model to be optimized; Applying a reinforcement learning algorithm, defining a reward function by combining multiple evaluation indicators, evaluating the adaptability scores of different plant combinations based on the reward function, optimizing the plant ecological adaptability prediction model to be optimized based on the adaptability scores, and obtaining a plant ecological adaptability prediction model, wherein the evaluation indicators include plant growth rate, stress resistance, and aesthetic value; Based on the plant ecological adaptability prediction model, the interactions between different plants and the impacts of different plants on the ecosystem are predicted and analyzed to generate ecological adaptability intelligent evaluation results.

7. The method according to claim 1, characterized in that The style transfer algorithm and the emotion perception interactive design method are used to integrate the aesthetic elements in the artwork and the user preference feedback with the first target planting combination and layout scheme to obtain the final target planting combination and layout scheme, including: Using the style transfer algorithm in deep learning to extract aesthetic elements from artworks, the aesthetic elements include color palette, texture features, and spatial layout patterns; Collect user preference feedback using emotion-aware interaction design methods to obtain user preferences and emotional response information to different landscape elements. The emotion-aware interaction design methods include questionnaire surveys, focus group discussions, and eye-tracking experiments. A cross-domain transfer learning model is constructed to integrate the aesthetic elements, the preference and emotional response information, and the first target planting combination and layout plan to obtain a final target planting combination and layout plan.

8. A landscape garden planting planning and management system based on terrain environment analysis, characterized in that: include: A collection module, for collecting comprehensive environmental and biodiversity data to generate a comprehensive terrain environment database, wherein the comprehensive environmental and biodiversity data includes surface images, meteorological historical data, soil type distribution maps, and biodiversity census information; A simulation module, for simulating the response differences of different plant genotypes under specific environmental conditions using a genetic algorithm based on the comprehensive terrain environment database to generate a plant ecological adaptability prediction model, and generating an ecological adaptability intelligent evaluation result based on the plant ecological adaptability prediction model; A generation module is used to construct a three-dimensional virtual ecosystem model based on the ecological adaptability intelligent evaluation result by using a generative adversarial network in deep learning to simulate the natural growth process of multiple plants in a selected area and the interaction between plants, generate an optimal planting combination and layout scheme to be optimized, and optimize the optimal planting combination and layout scheme to be optimized by combining a user interactive function and a collaborative filtering algorithm to obtain a first target planting combination and layout scheme; An optimization module, for integrating the aesthetic elements in the artwork and the user preference feedback with the first target planting combination and layout scheme by using a style transfer algorithm and an emotion-aware interactive design method, to obtain a final target planting combination and layout scheme; A management module is used to monitor the ecological environment of the planted area based on the key monitoring points and indicators determined in the final target planting combination and layout plan, obtain the existing planting ecological data, and perform landscape planting planning management based on the final target planting combination and layout plan and the existing planting ecological data.

9. A computing device, characterized in that It comprises a processing component and a storage component; the storage component stores one or more computer instructions; the one or more computer instructions are used to be called and executed by the processing component to implement a landscape planting planning and management method based on terrain environment analysis as described in any one of claims 1 to 7.

10. A computer storage medium, characterized in that: A computer program is stored, and when the computer program is executed by a computer, a landscape planting planning and management method based on terrain environment analysis as described in any one of claims 1 to 7 is implemented.

Images