Optimization method of vegetation greening layout

Abstract

The vegetation greening layout optimization method provided by the present application relates to the field of environmental engineering and garden design technology. The method obtains plant types and planting densities by performing homologous retrieval based on the factors affecting plant growth in the target area as constraints; calculates the high-frequency planting density threshold of the plant type; inputs the plant type into the type-attribute comparison table to match the time zone attribute, determines the plant combination and performs adaptive screening; generates an initial layout plan based on the vegetation layout design based on the adapted plant combination and the high-frequency planting density threshold; constructs a simulated growth environment to predict the growth and simulate the viewing of the layout plan; evaluates and assesses the feasibility of the simulated landscape based on the landscape evaluation function to determine the optimal layout plan. The method solves the technical problem of the lack of systematic analysis of plant growth, which leads to the inability to accurately configure vegetation and effectively predict and evaluate vegetation growth effects and landscape aesthetics, and achieves the technical effect of improving the accuracy and predictability of plant layout.

Description

Technical Field

[0001] The present invention relates to the technical field of environmental engineering and garden design, and in particular to a method for optimizing the layout of vegetation greening. Background Art

[0002] With the acceleration of urbanization and the emphasis on ecological and environmental protection, urban greening layout plays a vital role in enhancing urban aesthetics and improving the ecological environment. However, with the expansion of urban scale and the complexity of urban structure, the design and management of greening layout are also facing increasing challenges. Traditional greening layout methods often rely on the experience and intuitive judgment of gardeners, which may, to a certain extent, lead to uneven greening effects and increased maintenance costs in the later stages of plant growth. Traditional greening methods often ignore the specific needs and environmental adaptability of plant growth in plant selection and layout design, and fail to fully consider soil conditions, climate characteristics and terrain effects, all of which have a significant impact on plant growth and landscape effects. In addition, these methods are usually unable to effectively predict the dynamic changes in plant growth, resulting in the inability to adjust and optimize vegetation configuration in real time, affecting the quality and durability of greening.

[0003] In summary, the existing vegetation greening layout methods lack systematic analysis and real-time monitoring of plant growth, resulting in the inability to accurately configure vegetation, and the inability to effectively predict and evaluate the growth effect and landscape aesthetics after vegetation layout, which in turn causes technical problems such as loss of ecological benefits and economic efficiency, and poor greening quality and durability. Summary of the Invention

[0004] This application provides a method for optimizing the layout of vegetation and greening, which is used to solve the technical problems that the existing vegetation and greening layout methods lack systematic analysis and real-time monitoring of plant growth, resulting in the inability to accurately configure vegetation, and the inability to effectively predict and evaluate the growth effect and landscape aesthetics after vegetation layout, thereby causing losses in ecological benefits and economic efficiency, and poor greening quality and durability.

[0005] The present application provides a method for optimizing the layout of vegetation greening, which includes:

[0006] Collect plant growth influencing factors in the target area, use the plant growth influencing factors as constraints, perform homology retrieval based on garden big data, and obtain a sample plant information set, wherein the sample plant information includes plant type and planting density; determine multiple plant types based on the sample plant information set, and calculate multiple high-frequency planting density thresholds for the multiple plant types; input the multiple plant types into a type-attribute comparison table, match and obtain multiple time zone attributes, and use the expected plant diversity as a constraint to enumerate the multiple time zone attributes to determine multiple plant combinations, perform adaptation screening on the multiple plant combinations, and determine multiple adapted plant combinations; based on the multiple adapted plant combinations and the multiple The method comprises the following steps: performing vegetation layout design based on a high-frequency planting density threshold and generating multiple initial layout schemes; using ecological simulation software, constructing a simulated growth environment according to the plant growth influencing factors, and using the simulated growth environment to predict the growth of the multiple initial layout schemes after a predetermined period, and generating multiple growth prediction scenarios; performing simulated viewing of the multiple growth prediction scenarios based on a predetermined viewing strategy, obtaining multiple simulated landscape image sets, and evaluating the multiple simulated landscape image sets according to a landscape evaluation function to determine multiple optimized layout schemes; performing construction feasibility assessments on the multiple optimized layout schemes, determining the optimal layout scheme based on the assessment results, and executing vegetation layout in the target area.

[0007] One or more technical solutions provided in this application have at least the following technical effects or advantages:

[0008] The vegetation greening layout optimization method provided by the present application collects plant growth influencing factors in the target area, takes the plant growth influencing factors as constraints, performs homology retrieval based on garden big data, and obtains a sample plant information set, wherein the sample plant information includes plant type and planting density; determines multiple plant types based on the sample plant information set, and calculates multiple high-frequency planting density thresholds for the multiple plant types; inputs the multiple plant types into a type-attribute comparison table, matches multiple time zone attributes, and enumerates the multiple time zone attributes to meet the expected plant diversity as a constraint, determines multiple plant combinations, performs adaptation screening on the multiple plant combinations, and determines multiple adapted plant combinations; designs vegetation layout based on the multiple adapted plant combinations and the multiple high-frequency planting density thresholds, and generates multiple initial layout schemes; uses ecological simulation software to construct a simulated growth environment according to the plant growth influencing factors, and respectively screens the multiple plant combinations through the simulated growth environment. The method performs growth prediction after a predetermined period for each initial layout scheme to generate multiple growth prediction scenarios; simulates viewing of the multiple growth prediction scenarios based on a predetermined viewing strategy to obtain multiple simulated landscape image sets, and evaluates the multiple simulated landscape image sets according to a landscape evaluation function to determine multiple optimized layout schemes; conducts construction feasibility evaluation on the multiple optimized layout schemes, determines the optimal layout scheme based on the evaluation results, and executes vegetation layout in the target area, which solves the technical problems that the existing vegetation greening layout methods lack systematic analysis and real-time monitoring of plant growth, resulting in the inability to accurately configure vegetation, and the inability to effectively predict and evaluate the growth effect and landscape aesthetics after vegetation layout, which in turn causes losses in ecological benefits and economic efficiency, and poor greening quality and durability, and achieves the technical effect of improving the accuracy and predictability of plant layout, thereby ensuring the maximization of the aesthetics, ecological benefits and economic efficiency of vegetation layout, and ensuring greening quality and durability. BRIEF DESCRIPTION OF THE DRAWINGS

[0009] Figure 1 A flow chart of the vegetation greening layout optimization method is provided for this application.

[0010] Figure 2 A flow chart of garden big data mining in the vegetation greening layout optimization method is provided for this application. DETAILED DESCRIPTION

[0011] In order to make the purpose, technical solutions and advantages of this application more clear, the following further describes this application in detail with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain this application and are not intended to limit this application.

[0012] Examples, such as Figure 1 As shown, the present application provides a method for optimizing vegetation greening layout, the method comprising:

[0013] Step S100: collecting plant growth influencing factors in the target area, using the plant growth influencing factors as constraints, performing homologous search based on garden big data, and obtaining a sample plant information set, wherein the sample plant information includes plant type and planting density.

[0014] Specifically, factors affecting plant growth in the target area are first collected. These factors mainly include but are not limited to soil type, soil fertility, climate conditions (such as temperature and humidity), light conditions, and topography. These parameters are crucial for determining which plants can grow best in that area. For example, if an area has sufficient sunlight but poor soil drainage, it is suitable for growing light-loving and moisture-tolerant plants. The target area refers to an area where vegetation greening is about to be laid out, such as real estate parks, park greening, and traffic green belts.

[0015] After collecting growth-influencing factors, these factors are used as constraints to conduct a homology search using the garden big data platform. Garden big data refers to a database that contains extensive information on plant growth, plant species, historical vegetation layouts, and other examples. Homology search involves searching and identifying other datasets with the same or similar environmental characteristics based on known data about a specific environment or condition. Homology search leverages the garden big data platform to compare key growth-influencing factors such as soil type, climate, and light conditions, identifying plant species and planting density under similar conditions. This information reflects the adaptability and growth performance of plants in similar environments and can provide valuable reference and guidance for new vegetation layouts. This method allows the retrieval of sample plant information sets with similar growth conditions to the target area. This information set details the various plant types and their planting densities under similar conditions. Planting density refers to the number of plants planted within a given area. It is typically used to describe the distance between plants and the density of their distribution, and is calculated as the number of plants per unit area. Planting density is a critical agricultural and horticultural parameter because it directly affects plant growth, health, yield, and ultimately, landscape quality. For example, if the target area has a temperate climate and loam soil, then the plant types that successfully grow in temperate loam areas, such as oaks and pines, and the planting densities at which they successfully grow will be retrieved from the big data. Of course, this data is not only based on historical vegetation layout cases, but may also include information from experimental data or field tests to ensure the accuracy and practicality of the retrieval results.

[0016] By conducting homologous searches based on factors affecting plant growth and preliminarily determining plant species and planting density, an effective reference is provided for subsequent layout decisions. This not only improves product selection efficiency and decision-making speed, but also ensures the predictability and accuracy of the layout.

[0017] Step S200: determining a plurality of plant types based on the sample plant information set, and calculating a plurality of high-frequency planting density thresholds of the plurality of plant types.

[0018] Next, based on the sample plant information set, the performance and adaptability of various plant types in similar growing environments are analyzed. Plant types are selected not only based on their viability but also on their aesthetic value and ecological functions, such as providing shade, air purification, or enhancing biodiversity. For example, if the target area is located in an urban park, trees and shrubs with high ornamental value and low maintenance requirements, such as cherry trees and crape myrtles, may be preferred. Subsequently, a high-frequency planting density threshold is calculated for each plant type. This calculation is based on the planting density distribution of the corresponding plant type in the collected data, and the most frequently occurring planting density range is counted. The planting density threshold represents the optimal plant spacing that ensures healthy plant growth while achieving the desired landscape effect. For example, for lawn plants, the planting density might be calculated as the number of grass seeds planted per square meter to achieve uniform coverage without overcrowding. For urban greening, taking cherry trees as an example, historical data shows that in similar urban park settings, the planting density of cherry trees is typically 3-5 trees per 100 square meters. This data reflects the best practice planting density for ensuring healthy tree growth and a good visual effect of blooming flowers. In this way, a standard range of planting densities can be developed for each plant type, thus guiding the implementation of actual vegetation layouts.

[0019] Through the above steps, the appropriate plant types and their planting density can be scientifically determined, which greatly improves the practicality and feasibility of vegetation greening layout and ensures that the final greening effect is both beautiful and eco-friendly.

[0020] Step S300: Input the multiple plant types into the type-attribute comparison table, match to obtain multiple time zone attributes, and use the expected plant diversity as a constraint to enumerate the multiple time zone attributes to determine multiple plant combinations, perform adaptation screening on the multiple plant combinations, and determine multiple adapted plant combinations.

[0021] Optionally, multiple plant types are classified according to their seasonal characteristics to ensure that the expected greening effect can be displayed throughout the year in the designed vegetation layout and that the requirements of ecological diversity are met. Specifically, each plant is first classified into its best display season, that is, the time zone attribute, including spring, summer, autumn, winter and all seasons, based on its growth habits and seasonal changes. In this step, the season of the plant (that is, the time zone attribute) is entered into a type-attribute comparison table. For example, cherry blossoms bloom mainly in spring and are therefore classified in the spring plant category; certain evergreen tree species, such as pine trees, are classified as all-season plants because of their year-round evergreen characteristics.

[0022] Subsequently, based on the principle of plant diversity as a constraint, a diverse plant display is ensured in each season. This means that in any given season, the park or green area can present a rich and colorful vegetation state, thereby enhancing the landscape's attractiveness and ecological value. This constraint requires that at least a predetermined number of plant species be included in each season to ensure seasonal visual and ecological diversity. Next, plant species are enumerated based on classification and diversity constraints, and multiple plant combination cases are generated by randomly combining plant types from different seasons. For example, in spring, a combination of cherry blossoms, tulips, and forsythia might be used; in summer, sunflowers, crape myrtles, and lavender might be selected. Furthermore, each generated plant combination is then subjected to an adaptation screening process, which takes into account inter-plant compatibility (such as root competition and light requirements), maintenance requirements, and the harmony of the overall landscape design. Adaptation screening determines which plant combinations will coexist well in the actual environment and achieve the intended greening effect.

[0023] Through the above steps, the seasonal diversity and aesthetics of vegetation layout are effectively achieved, while also meeting the needs of ecological diversity and sustainable development. This plant combination screening method based on seasonal attributes and diversity constraints provides a scientific and practical solution for modern urban greening.

[0024] Step S400: performing vegetation layout design based on the multiple adaptive plant combinations and the multiple high-frequency planting density thresholds to generate multiple initial layout schemes.

[0025] Furthermore, detailed information on the design area's topography, soil type, and light conditions is obtained using geographic information systems and site survey data. This information is crucial for ensuring the suitability of plant species and planting density. For each plant combination, corresponding high-frequency planting density thresholds are applied to the layout plan. The layout design also considers the plant's growth habits, mature size, seasonal variations, and light and water requirements. Planners must ensure adequate spacing between plants to support healthy growth, while also considering aesthetics and visual continuity. Using software tools or manual calculations, plants are arranged within the layout in a manner that optimizes both aesthetics and functionality. Ultimately, all data and parameters are combined to generate multiple initial vegetation layout proposals. Each proposal should detail the plant location, species, and projected growth and development. Once the initial proposal is finalized, it can be reviewed internally for feasibility, cost-effectiveness, and expected ecological benefits. Adjustments can be made, if necessary, to better suit geographic and ecological conditions or to better meet the needs of clients and the public.

[0026] Through the above steps, a systematic approach is provided to design and implement vegetation layout, which ensures the healthy growth of plants and the overall beauty of the landscape design, while also considering the maximization of ecological and economic benefits.

[0027] Step S500: using ecological simulation software to construct a simulated growth environment according to the plant growth influencing factors, and using the simulated growth environment to perform growth predictions on the multiple initial layout schemes after a predetermined period to generate multiple growth prediction scenarios.

[0028] Exemplarily, ecological simulation software is a computer program or system specially designed to simulate and analyze the interactions and dynamic changes of various factors in an ecosystem. This type of software uses multidisciplinary knowledge such as ecology, botany, meteorology, and soil science, combined with mathematical models and algorithms, to predict the behavior and development trends of ecosystems under specific environmental conditions. Therefore, ecological simulation software is used to simulate the plant growth simulation of the layout scheme. First, all growth influencing factor data related to the target area are input. These data include but are not limited to soil pH, nutrients, average annual rainfall, temperature range, light intensity, etc. These parameters are crucial for accurately simulating the plant growth environment. Appropriate simulation parameters are set in the software, such as the length of the growth cycle (for example, 3 years, 5 years, or 10 years), simulated seasonal changes, etc. These parameters will help the software to more accurately predict the growth and maturation process of the plant.

[0029] Next, the ecological simulation software simulates the development of each plant species over a set growth cycle based on the input environmental data and plant characteristics, including growth indicators such as plant height, crown width, and leaf color changes. Finally, the software generates detailed growth forecast scenarios for all plant species. These scenarios visually demonstrate plant growth at various points in the future, such as tree coverage and shrub density.

[0030] Through the above steps, advanced ecological simulation technology can be effectively used to predict and optimize greening projects, ensuring the scientific nature and long-term sustainability of vegetation layout.

[0031] Step S600: simulating viewing of the plurality of growth prediction scenes based on a predetermined viewing strategy to obtain a plurality of simulated landscape image sets, and respectively evaluating the plurality of simulated landscape image sets according to a landscape evaluation function to determine a plurality of optimized layout schemes.

[0032] Optionally, determine a predetermined viewing strategy. Set a series of viewing points based on the geographical characteristics of the target area and the public access routes. Each viewing point is equipped with multiple viewing angles, covering the perspectives of viewing vegetation from different directions and heights. For example, viewing points may be set at the entrance of the park, in a rest area, or around a water body, and the viewing angles include looking straight ahead, looking down, and looking up. Then, use ecological simulation software and three-dimensional visualization tools to generate vegetation layout views from each viewing point and angle according to the above viewing strategy. These views reflect the growth status of plants in different seasons and time periods, as well as their visual effects in the landscape. In this process, the views of each viewing point and angle are captured and saved as images to form a set of simulated landscape images. These image sets will be used for subsequent evaluation and analysis to determine which vegetation layout schemes are the most visually attractive and meet the design goals.

[0033] Next, each simulated landscape image set was evaluated using a landscape evaluation function. This function includes multiple evaluation metrics, such as plant color harmony, structural diversity, visual impact, and integration with the surrounding environment. Each metric is assigned a weight and adjusted based on its importance in the overall aesthetic and functional aspects. Finally, the strengths and weaknesses of each layout scheme were analyzed based on the results of the landscape evaluation function. High-scoring schemes indicate that their visual and functional effects meet expectations, while low-scoring ones may require adjustments to plant species, location, or density. For example, in a downtown park design project, five main viewing points were identified, each with three viewing angles. Landscape image sets for spring and autumn were generated using simulation software and evaluated using the landscape evaluation function. The results showed that the cherry blossom layout at the entrance scored highly in spring, but the visual effect was poor in autumn due to the yellowing of the cherry blossom leaves, which lacked contrast with the evergreens. Therefore, the placement and number of evergreens were adjusted to enhance the visual effect in autumn. These steps not only optimized the visual aesthetics of the vegetation layout scheme but also improved its ability to adapt to seasonal changes, ensuring a consistently attractive landscape throughout the year.

[0034] Step S700: Conduct construction feasibility assessments on each of the plurality of optimized layout schemes, determine the optimal layout scheme based on the assessment results, and execute vegetation layout in the target area.

[0035] Specifically, a constructability assessment was conducted for each optimized layout to ensure that the selected option was not only visually and ecologically optimal, but also technically and economically feasible. This process involved multiple assessments, including cost estimation, construction technical requirements, long-term maintenance, and environmental impact assessment. Based on these assessments, the optimal vegetation layout was determined and implemented in the target area.

[0036] In this embodiment, the construction feasibility assessment includes technical, economic, and environmental feasibility assessments. The technical feasibility assessment evaluates terrain suitability and construction difficulty, specifically assessing whether the terrain is suitable for the selected plants. For example, some plants may require good drainage, which other terrains may not offer. It also considers the construction techniques and equipment required for plant planting and landscape construction. For example, large trees may require specialized lifting equipment for implantation. The economic feasibility assessment provides a cost estimate for the required materials, labor, and equipment, including all related expenses such as plant purchase, soil improvement, and irrigation system installation. The environmental feasibility assessment considers ecological impact and sustainability, assessing the impact of the selected plants on the local ecosystem to ensure the proposal will not negatively impact the local ecology. It also considers the long-term maintenance requirements and sustainability of the plants, such as selecting drought-tolerant plants to reduce water consumption. Finally, the technical, economic, and environmental assessment results of all options are summarized and compared. Based on the evaluation results, the expert team and project manager discuss the strengths and weaknesses of each option and select the one that performs best across all evaluation criteria. This typically involves balancing various factors, such as cost-effectiveness, construction difficulty, long-term maintenance requirements, and environmental impact. The vegetation layout is completed by arranging the vegetation on site according to the determined optimal solution. Through the above steps, not only the feasibility and economic feasibility of the vegetation layout plan are ensured, but also the environmental sustainability and ecological impact are taken into consideration, thus achieving a fully optimized greening solution.

[0037] Furthermore, to obtain the sample plant information set, step S100 of this application further includes:

[0038] Step S110: collecting factors affecting plant growth in the target area, wherein the factors affecting plant growth include soil information, climate information, and landform information.

[0039] Step S120: extracting features from the soil information, climate information, and landform information to construct a soil feature matrix, a climate feature matrix, and a landform feature matrix.

[0040] Step S130: using the soil characteristic matrix, climate characteristic matrix and landform characteristic matrix as constraints, data mining is performed based on garden big data to obtain the sample plant information set.

[0041] Optionally, define key factors affecting plant growth within the target area, including soil, climate, and geomorphological information. This information can be collected through field measurements, analysis of historical climate data, and geological surveys. For example, soil samples can be analyzed to determine their pH, organic matter content, and texture; climate information includes annual average temperature, precipitation, and sunshine hours; and geomorphological information focuses on the slope, altitude, and aspect of the terrain.

[0042] Furthermore, feature extraction is performed on the collected soil, climate, and landform data, using statistical and geographic information system software to identify and quantify key variables influencing plant growth. For example, features extracted from soil sample data might include nutrient concentrations, drainage capacity, and soil type. The extracted features are then used to construct soil, climate, and landform feature matrices. These matrices serve as input for subsequent data mining. Each matrix contains data from multiple dimensions, detailing the characteristics of each environmental factor. The constructed feature matrices are then fed into a garden big data analysis system, which uses them as constraints to identify plant species that are well-suited to specific environmental conditions using data mining techniques. This process uses machine learning algorithms to predict the growth performance and survival rates of different plants under specific environmental conditions. Ultimately, based on the data mining results, a sample plant information set is generated, containing recommended plant species and their planting densities. For example, if data mining indicates that a particular plant performs well under specific soil and climate conditions, that plant and its appropriate planting density are included in the information set. For example, in an urban park project, data mining results showed that cherry trees and crape myrtles grow best in soils with high organic matter content and moderate drainage. This information will be used to guide the layout design of these plants in the park to ensure that they can thrive in the most suitable environment.

[0043] Through the above steps, scientific, data-driven plant selection and layout recommendations can be effectively provided for the vegetation layout of a specific area, thereby maximizing the ecological benefits and aesthetics of the vegetation.

[0044] Furthermore, if Figure 2 As shown, data mining is performed based on garden big data, and step S130 of this application also includes:

[0045] Step S131: performing data mining based on garden big data to obtain first search data, wherein the first search data includes a first soil characteristic, a first climate characteristic, and a first landform characteristic.

[0046] Step S132: performing similarity analysis on the soil feature matrix and the first soil feature according to a predetermined similarity comparison algorithm to determine a first similarity.

[0047] Step S133: If the first similarity is greater than a predetermined threshold, a similarity analysis is performed on the climate characteristic matrix and the first climate characteristic to determine a second similarity.

[0048] Step S134: If the second similarity is greater than a predetermined threshold, a similarity analysis is performed on the landform feature matrix and the first landform feature to determine a third similarity.

[0049] Step S135: If the third similarity is greater than a predetermined threshold, the first search data is added to the sample plant information set.

[0050] Furthermore, a predetermined similarity analysis algorithm is used to perform multi-stage data comparison and screening to ensure that the plant species ultimately selected are most suitable for the designated area. Specifically, a preliminary data mining is first performed using garden big data resources to obtain the first search data, including retrieving the first soil characteristics, first climate characteristics, and first landform characteristics from a large amount of stored environmental and plant growth data. These characteristics are extracted from environmental conditions known to have a positive impact on plant growth and reflect a set of ecological environments that may be similar to the target area.

[0051] The soil characteristics of the first search data retrieved are analyzed and compared with the soil characteristic matrix of the target area using a predetermined similarity comparison algorithm to determine a first similarity. This comparison algorithm calculates a similarity score based on a set of quantitative indicators, such as soil pH, organic matter content, and texture. If the first similarity exceeds a predetermined threshold, indicating a high degree of similarity between the first soil characteristic and the target area's soil, the same similarity analysis is then performed on the climate characteristics to calculate a second similarity between the first climate characteristic and the climate characteristic matrix of the target area. Climate characteristics may include annual average temperature, precipitation, and sunshine hours. The second similarity is also calculated based on a predetermined algorithm to assess the degree of match between the two. If the second similarity also exceeds a predetermined threshold, the geomorphological characteristics are analyzed. This step involves comparing the first geomorphological characteristics with the geomorphological matrix of the target area to determine a third similarity. The geomorphological analysis may focus on factors such as terrain slope and altitude. The third similarity score determines whether the data set is added to the sample plant information set. If the third similarity also exceeds the threshold, it indicates that the first search data is highly similar to the target area in terms of soil, climate and landform. Therefore, it will be added to the sample plant information set. This information set will be used for vegetation layout design to ensure that the selected plant species and planting strategies are highly consistent with environmental conditions, thereby improving the vegetation success rate and ecological benefits.

[0052] Through the above steps, not only the scientificity and accuracy of plant selection are improved, but also the adaptability and sustainability of vegetation layout are optimized, providing solid data support for the realization of efficient and eco-friendly greening projects.

[0053] Furthermore, to obtain multiple high-frequency planting density thresholds, step S200 of the present application further includes:

[0054] Step S210: randomly selecting a first plant type from the plurality of plant types, and performing planting density extraction on the sample plant information set based on the first plant type to obtain a first density set.

[0055] Step S220: determining a first initial density threshold based on the maximum density value and the minimum density value of the first density set, dividing the first initial density threshold according to a predetermined step size, and determining a plurality of first initial density intervals.

[0056] Step S230: Count the number of data in multiple first initial density intervals to obtain multiple first frequencies, select the first initial density interval corresponding to the first frequency greater than the predetermined frequency threshold and set it as the first high-frequency density interval, construct a first high-frequency planting density threshold based on the multiple first high-frequency density intervals, and add it to the multiple high-frequency planting density thresholds.

[0057] For example, a plant type is randomly selected from the sample plant information set as the first plant type. This selection relies on the diversity and completeness of the sample plant information set to ensure that a wide range of plant types are selected to fairly evaluate the planting density of different plants. Based on the selected first plant type, all relevant planting density data are extracted from the information set to form a first density set. This data set includes the planting density values of the plant type actually used in historical records, and these density values are collected from multiple different locations and conditions.

[0058] Further, the first density set is analyzed to determine its maximum density value and minimum density value, which reflect the planting density limit of the plant type under different conditions. Then, a first initial density threshold is set based on these two extreme values, and this density range is divided into multiple first initial density intervals according to a predetermined step size (for example, one plant is added per square meter). Data statistics are performed on each first initial density interval, and the number of data in each interval, that is, the first frequency, is calculated to obtain multiple first frequencies. This step is intended to identify the most common planting density intervals in actual applications. The interval whose first frequency is greater than the predetermined frequency threshold is selected and defined as the first high-frequency density interval, which represents the most commonly used and most effective density range in actual planting. A first high-frequency planting density threshold is constructed based on multiple first high-frequency density intervals. This threshold provides a scientific basis for designers and gardeners to guide them in using the most effective planting density in actual vegetation layout. Among them, the predetermined step size and predetermined frequency threshold can be set according to actual needs and are not limited here.

[0059] Through the above steps, not only a systematic and scientific method is provided to determine the ideal planting density of plants, but also the aesthetics and growth effect of plant layout are ensured, and the practicality and sustainability of vegetation design are enhanced.

[0060] Furthermore, the plurality of plant combinations are subjected to adaptation screening, and step S300 of the present application further includes:

[0061] Step S310: randomly selecting a first plant combination from the plurality of plant combinations, performing a big data search with the first plant combination and the plant growth influencing factors as constraints, and obtaining a plurality of plant survival rate sets.

[0062] Step S320: abnormal state triggering judgment is performed on the plurality of plant survival rate sets respectively according to a predetermined abnormal rule to determine a first abnormal proportion, wherein if the survival rate of any plant in the plant survival rate set is less than a predetermined survival rate threshold, an abnormal state is triggered.

[0063] Step S330: If the first abnormality ratio is less than a predetermined abnormality threshold, the first plant combination is set as an adapted plant combination; otherwise, the first plant combination is discarded.

[0064] Specifically, one of multiple pre-designed plant combinations is randomly selected as the first plant combination. This step ensures that each plant combination has an equal opportunity to be evaluated, making the screening process fair and unbiased. Furthermore, using the garden big data platform, data is retrieved based on the first plant combination and its associated factors affecting plant growth (such as soil type and climate conditions) to obtain a set of plant survival rates for this combination. This set includes historical data on the survival of plants in this combination under similar environmental conditions.

[0065] Furthermore, a predetermined exception rule is set to evaluate whether the plant survival rate meets the minimum requirement. Specifically, the plant survival rate set is analyzed to determine whether any plant has a survival rate below a predetermined survival rate threshold (e.g., 60%). This threshold can be determined based on sufficient scientific research and practical experience to ensure the overall health and growth potential of the plant combination. If the survival rate of any plant in the plant survival rate set is less than the predetermined survival rate threshold, an abnormal state is triggered. The proportion of plants that trigger the abnormal state, i.e., the first abnormality ratio, is calculated. This value represents the proportion of plants in the plant combination that do not meet the minimum survival rate requirement. If the first abnormality ratio is less than the predetermined abnormality threshold (e.g., if the abnormality ratio is less than 20%), the first plant combination is considered to have high overall adaptability and survival potential and is therefore set as an adapted plant combination. Conversely, if the abnormality ratio is higher than this threshold, it indicates that the survival rate of the plant combination in the target environment may not meet expectations and is therefore discarded from consideration. The predetermined abnormality threshold can be determined based on actual conditions.

[0066] Through the above steps, it is possible to effectively ensure that the selected plant combination has the highest survival rate and optimal growth conditions in a specific environment, improve the layout accuracy, and thus enhance the sustainability and ecological benefits of the vegetation layout.

[0067] Furthermore, to obtain multiple simulated landscape image sets, step S600 of the present application further includes:

[0068] Step S610: configuring a predetermined viewing strategy, wherein the predetermined viewing strategy includes a plurality of predetermined viewing points, and each predetermined viewing point includes a plurality of viewing angles.

[0069] Step S620: Based on the multiple predetermined viewing points and multiple viewing angles, viewing images of the multiple growth prediction scenes are collected to obtain multiple simulated landscape image sets.

[0070] Optionally, multiple pre-defined viewing points are selected as potentially important viewing locations, such as the park's entrance, central lake, and rest areas. Each viewing point is further subdivided into multiple viewing angles, encompassing perspectives from different directions and heights, such as frontal, side, and overhead views. The pre-defined viewing strategy is based on the overall landscape design priorities and viewing value, ensuring that important vegetation elements and landscape features are displayed from the optimal perspective, thereby enhancing the visitor viewing experience and the visual appeal of the site. Furthermore, advanced graphics and rendering software is used to perform visual simulations of each growth prediction scenario based on each viewing point and viewing angle, including simulating lighting and shadow effects in different seasons and time periods, as well as the actual appearance of plants after maturity. High-quality images are captured from each viewing angle and synthesized into a simulated landscape image set. Each image set represents the predicted vegetation layout effect as seen from a specific viewing point and angle, providing rich visual data for further landscape assessment.

[0071] Through the above steps, we can not only systematically capture and evaluate the visual effects of vegetation layout, but also optimize vegetation layout based on actual viewing strategies, ensuring that the final design scheme is both beautiful and practical, meeting the public's viewing and functional needs.

[0072] Furthermore, to determine multiple optimized layout solutions, step S600 of the present application further includes:

[0073] Step S630: Using the garden expert system, respectively evaluate the multiple simulated landscape image sets in terms of landscape color, plant size, and plant morphology, and determine multiple color evaluation coefficient sets, multiple size evaluation coefficient sets, and multiple morphology evaluation coefficient sets.

[0074] Step S640: According to the landscape evaluation function, comprehensively evaluate the multiple color evaluation coefficient sets, multiple size evaluation coefficient sets, and multiple form evaluation coefficient sets, determine multiple landscape evaluation coefficients, and arrange them from large to small to generate a landscape evaluation coefficient sequence.

[0075] Step S650: selecting the initial layout schemes corresponding to the first Q landscape evaluation coefficients of the landscape evaluation coefficient sequence and setting them as optimized layout schemes to obtain the multiple optimized layout schemes, wherein Q is an integer greater than 3 and less than 10.

[0076] Furthermore, to construct a landscape evaluation function, step S640 of this application further includes:

[0077] The expression of the landscape evaluation function is:

[0078]

[0079] Among them, F is the landscape evaluation coefficient, M is the number of scheduled viewing spots, m represents any one of the M scheduled viewing spots, and w m is the weight of the mth scheduled viewing point, N is the number of viewing angles of the mth scheduled viewing point, n represents any one of the N viewing angles, w n is the weight of the nth viewing angle, v1 is the color weight, v2 is the size weight, v3 is the shape weight, AR is the color evaluation coefficient, BR is the size evaluation coefficient, and CR is the shape evaluation coefficient.

[0080] Specifically, a garden expert system is configured to receive and process simulated landscape image sets. The system should have advanced image analysis capabilities that can identify and evaluate features such as color, size, and morphology in the images. Evaluation parameters are set in the system, including weights for color, size, and morphology (v1, v2, v3). These parameters are pre-set based on the design goals and expected visual effects of the vegetation layout. Furthermore, the simulated landscape images for each predetermined viewing point and angle are uploaded to the expert system. The system automatically identifies key visual elements in the image, such as the color vividness, size ratio, and morphological structure of the plants, and scores the color, size, and morphology of each image, generating a color rating coefficient (AR), a size rating coefficient (BR), and a morphological rating coefficient (CR). The scores are obtained based on advanced image analysis techniques such as color histogram matching, object size analysis, and morphological recognition algorithms.

[0081] Further, according to the formula Calculate the comprehensive landscape evaluation coefficient F for each image set, taking into account the importance of each viewing point (w m ) and the effect of each angle (w n Next, all calculated F-scores are ranked from highest to lowest to identify the best-performing vegetation layouts. Finally, based on the ranking results, the top Q high-scoring layouts are selected as the final optimized layouts, based on a comprehensive consideration of the vegetation's aesthetics, ecological benefits, and sustainability.

[0082] Through the above evaluation and selection process, the vegetation layout plan is optimized in aesthetics, ecology and function, meeting the public's viewing and functional needs while maintaining the sustainability and environmental friendliness of the design.

[0083] Through the technical solutions of the above embodiments, the vegetation greening layout optimization method provided by this application solves the technical problems that the existing vegetation greening layout methods lack systematic analysis and real-time monitoring of plant growth, resulting in the inability to accurately configure vegetation, and the inability to effectively predict and evaluate the growth effect and landscape aesthetics after vegetation layout, thereby causing losses in ecological benefits and economic efficiency, and poor greening quality and durability. It achieves the goal of improving the accuracy and predictability of plant layout, thereby ensuring the maximization of the aesthetics, ecological benefits and economic efficiency of vegetation layout, and guaranteeing the technical effect of greening quality and durability.

[0084] The technical features of the above embodiments can be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0085] The above-described embodiments merely represent several implementation methods of the present application. While the descriptions are relatively specific and detailed, they should not be construed as limiting the scope of the present invention. It should be noted that a person skilled in the art may make various modifications and improvements without departing from the scope of the present application, and such modifications and improvements are all within the scope of protection of the present application.

Claims

1. A method for optimizing vegetation greening layout, characterized in that: include: Collect plant growth influencing factors in the target area, use the plant growth influencing factors as constraints, perform homology search based on garden big data, and obtain a sample plant information set, wherein the sample plant information includes plant type and planting density; determining a plurality of plant types based on the sample plant information set, and calculating a plurality of high-frequency planting density thresholds of the plurality of plant types; Inputting the multiple plant types into a type-attribute comparison table, matching to obtain multiple time zone attributes, enumerating based on the multiple time zone attributes to determine multiple plant combinations, performing adaptation screening on the multiple plant combinations, and determining multiple suitable plant combinations; Performing vegetation layout design based on the multiple adaptive plant combinations and the multiple high-frequency planting density thresholds to generate multiple initial layout schemes; Using ecological simulation software, constructing a simulated growth environment based on the plant growth influencing factors, and using the simulated growth environment to perform growth predictions on the multiple initial layout schemes after a predetermined period to generate multiple growth prediction scenarios; Performing simulated viewing of the plurality of growth prediction scenes based on a predetermined viewing strategy to obtain a plurality of simulated landscape image sets, and evaluating the plurality of simulated landscape image sets according to a landscape evaluation function to determine a plurality of optimized layout schemes; Conducting feasibility assessments on each of the plurality of optimized layout schemes, determining an optimal layout scheme based on the assessment results, and executing vegetation layout in the target area; Acquire multiple simulated landscape image sets, including: Configuring a predetermined viewing strategy, wherein the predetermined viewing strategy includes a plurality of predetermined viewing points, and each predetermined viewing point includes a plurality of viewing angles; Based on the multiple predetermined viewing points and multiple viewing angles, viewing images of the multiple growth prediction scenes are collected to obtain multiple simulated landscape image sets; Identify multiple optimized layout options, including: By using a garden expert system, the plurality of simulated landscape image sets are evaluated for landscape color, plant size, and plant morphology, and a plurality of color evaluation coefficient sets, a plurality of size evaluation coefficient sets, and a plurality of morphology evaluation coefficient sets are determined; According to the landscape evaluation function, the plurality of color evaluation coefficient sets, the plurality of size evaluation coefficient sets, and the plurality of morphology evaluation coefficient sets are comprehensively evaluated to determine a plurality of landscape evaluation coefficients, and the coefficients are arranged from large to small to generate a landscape evaluation coefficient sequence; Selecting the initial layout schemes corresponding to the first Q landscape evaluation coefficients of the landscape evaluation coefficient sequence and setting them as optimized layout schemes to obtain the multiple optimized layout schemes, wherein Q is an integer greater than 3 and less than 10; Construct a landscape evaluation function, including: The expression of the landscape evaluation function is: in, is the landscape evaluation coefficient, is the number of scheduled viewing spots, m represents any one of the M scheduled viewing spots, is the weight of the mth scheduled viewing point, is the number of viewing angles of the mth scheduled viewing point, Represents any one of the N viewing angles, is the weight of the nth viewing angle, is the color weight, is the size weight, is the morphological weight, is the color evaluation coefficient, is the size evaluation coefficient, is the morphological evaluation coefficient.

2. The vegetation greening layout optimization method according to claim 1, characterized in that: Get a sample plant information set including: Collect factors affecting plant growth in the target area, including soil information, climate information, and landform information; Extracting features of the soil information, climate information, and landform information to construct a soil feature matrix, a climate feature matrix, and a landform feature matrix; Taking the soil characteristic matrix, climate characteristic matrix and landform characteristic matrix as constraints, data mining is performed based on garden big data to obtain the sample plant information set.

3. The vegetation greening layout optimization method according to claim 2, characterized in that: Data mining based on garden big data, including: Performing data mining based on the garden big data to obtain first search data, wherein the first search data includes a first soil characteristic, a first climate characteristic, and a first landform characteristic; Performing a similarity analysis on the soil feature matrix and the first soil feature according to a predetermined similarity comparison algorithm to determine a first similarity; If the first similarity is greater than a predetermined threshold, performing a similarity analysis on the climate characteristic matrix and the first climate characteristic to determine a second similarity; If the second similarity is greater than a predetermined threshold, performing a similarity analysis on the geomorphic feature matrix and the first geomorphic feature to determine a third similarity; If the third similarity is greater than a predetermined threshold, the first search data is added to the sample plant information set.

4. The vegetation greening layout optimization method according to claim 1, characterized in that: Multiple high-frequency planting density thresholds are obtained, including: randomly selecting a first plant type from the plurality of plant types, and performing planting density extraction on the sample plant information set based on the first plant type to obtain a first density set; determining a first initial density threshold based on a maximum density value and a minimum density value of the first density set, dividing the first initial density threshold according to a predetermined step size to determine a plurality of first initial density intervals; Count the number of data in multiple first initial density intervals to obtain multiple first frequencies, select the first initial density interval corresponding to the first frequency greater than the predetermined frequency threshold and set it as the first high-frequency density interval, construct a first high-frequency planting density threshold based on the multiple first high-frequency density intervals, and add it to the multiple high-frequency planting density thresholds.

5. The vegetation greening layout optimization method according to claim 1, characterized in that: Performing adaptation screening on the multiple plant combinations comprises: randomly selecting a first plant combination from the plurality of plant combinations, performing a big data search with the first plant combination and the plant growth influencing factors as constraints, and obtaining a plurality of plant survival rate sets; Performing abnormal state triggering judgment on each of the plurality of plant survival rate sets according to a predetermined abnormality rule to determine a first abnormality ratio, wherein if the survival rate of any plant in the plant survival rate set is less than a predetermined survival rate threshold, an abnormal state is triggered; If the first abnormality ratio is less than a predetermined abnormality threshold, the first plant combination is set as an adapted plant combination; otherwise, the first plant combination is discarded.

Images